anderssoegaard

Anders Søgaard

Anders

Professor in Natural Language Processing and Machine Learning at the University of Copenhagen. Jointly affilliated with the Dpt. of Computer Science, the Dpt. of Philosophy, the Pioneer Centre for Artificial Intelligence, and the Center for Social Data Science. Previously at University of Potsdam, Amazon Core Machine Learning, and Google Research. Father of three and a published poet.

Academic Books

Cover Cover Cover Cover

Publications

2024

Søgaard, Anders. 2024. Identity Theory and Falsifiability. Acta Analytica. PDF

Fierro, Constanza; Garneau, Nicolas; Bugliarello, Emanuele; Kementchedjhieva, Yova; Søgaard, Anders. 2024. MuLan: A Study of Fact Mutability in Language Models. North American Chapter of the Association for Computational Linguistics (NAACL). Mexico City, Mexico.

van Zee, Anna Katrine; van Zee, Marc; Søgaard, Anders. 2024. Group Fairness in Multilingual Speech Recognition Models. Findings of the North American Chapter of the Association for Computational Linguistics (NAACL). Mexico City, Mexico.

Hansen, Victor Petrén Bach; Neerkaje, Atula Tejaswi; Sawhney, Ramit, Flek, Lucie; Søgaard, Anders. 2024. The Impact of Differential Privacy on Group Disparity Mitigation. Findings of the North American Chapter of the Association for Computational Linguistics (NAACL). Mexico City, Mexico.

Søgaard, Anders; Kappel, Klemens; Grünbaum, Thor. 2024. On Hedden’s Proof that Machine Learning Fairness Metrics are Flawed. Inquiry. PDF

Søgaard, Anders. 2024. What’s Lost When a Language Dies? Intercultural Pragmatics.

Søgaard, Anders. 2024. On the Opacity of Deep Neural Networks. Canadian Journal of Philosophy.

Brandl, Stephanie; Eberle, Oliver; Ribeiro, Tiago; Søgaard, Anders; Hollenstein, Nora. 2024. Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations. The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (COLING-LREC). Torino, Italy. ArXiv

Karamolegkou, Antonia; Rust, Philip; Cao, Yong; Cui, Ruixiang; Hershcovich, Daniel; Søgaard, Anders. 2024. Vision-Language Models under Cultural and Inclusive Considerations. ICLR Workshop on Global AI Cultures. Vienna, Austria.

2023

Søgaard, Anders. 2023. Can Machines Be Trustworthy? AI & Ethics. PDF

Li, Jiaang; Karamolegkou, Antonia; Kementchedjhieva, Yova; Abdou, Mostafa; Lehmann, Sune Lehmann; Søgaard, Anders. 2023. Structural Similarities Between Language Models and Neural Response Measurements. NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations. New Orleans, LA. ArXiv

Christiansen, Jonathan; Gammelgaard, Mathias; Søgaard, Anders. 2023. Large language models partially converge toward human-like concept organization. NeurIPS 2023 Workshop on Symmetry and Geometry in Neural Representations. New Orleans, LA. PDF

Li, Jiaang; Kementchedjhieva, Yova; Søgaard, Anders. 2023. Implications of the Convergence of Language and Vision Model Geometries. ArXiv:2302.06555. ArXiv

Søgaard, Anders; Kappel, Klemens; Grünbaum, Thor. 2023. On Hedden’s Proof that Machine Learning Fairness Metrics are Flawed. NeurIPS Workshop on Algorithmic Fairness Through the Lens of Time. New Orleans, LA. Workshop

Ribeiro, Tiago; Brandl, Stephanie; Søgaard, Anders; Hollenstein, Nora. 2023. WebQAmGaze: A Multilingual Webcam Eye-Tracking-While-Reading Dataset. ArXiv:2303.17876. ArXiv

Karamolegkoy, Antonia; Li, Jiaang; Zhou, Li; Søgaard, Anders. 2023. Copyright Violations and Large Language Models. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2023. Singapore, Singapore. PDF

Rust, Phillip; Søgaard, Anders. 2023. Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models. The 40th International Conference on Machine Learning (ICML). Honolulu, Hawaii. PDF

Cui, Ruixiang; Lee, Seolhwa; Hershcovich, Daniel; Søgaard, Anders. 2023. What does the Failure to Reason with “Respectively’’ in Zero/Few-Shot Settings Tell Us about Language Models? The 61st Annual Meeting of the Association for Computational Linguistics (ACL). Toronto, Canada. PDF

Chalkidis, Ilias; Garneau, Nicolas; Goanta, Catalina; Katz, Daniel; Søgaard, Anders. 2023. LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development. The 61st Annual Meeting of the Association for Computational Linguistics (ACL). Toronto, Canada. PDF

Jakobsen, Terne; Cabello, Laura; Søgaard, Anders. 2023. Being Right for Whose Right Reasons? The 61st Annual Meeting of the Association for Computational Linguistics (ACL). Toronto, Canada. PDF

Karamolegkou, Antonia; Abdou, Mostafa; Søgaard, Anders. 2023. Mapping Brains with Language Models: A Survey. The 61st Annual Meeting of the Association for Computational Linguistics (ACL). Toronto, Canada. ArXiv

Søgaard, Anders. 2023. Grounding the Vector Space of an Octopus: Word Meaning from Raw Text. Minds and Machines 33 (1), 33-54. PDF

Lee, Seolhwa; Søgaard, Anders. 2023. Private Meeting Summarization Without Performance Loss. The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. Taipei, Taiwan. PDF

Cabello, Laura; Jørgensen, Anna Katrine; Søgaard, Anders. 2023. On the Independence of Association Bias and Empirical Fairness in Language Models. The ACM Conference on Fairness, Accountability, and Transparency 2023. Chicago, IL. PDF

Søgaard, Anders; Hershcovich, Daniel; de Lhoneux, Miryam. 2023. A Two-Sided Discussion of Preregistration of NLP Research. The 16th conference of the European Chapter of the Association for Computational Linguistics (EACL). Dubrovnik, Croatia. PDF

Kementchedjhieva, Yova; Søgaard, Anders. 2023. Grammatical Error Correction through Round-Trip Machine Translation. Findings of The 16th conference of the European Chapter of the Association for Computational Linguistics (EACL). Dubrovnik, Croatia. PDF

Jørgensen, Anna Katrine; Søgaard, Anders. 2023. Rawlsian AI Fairness Loopholes. AI & Ethics 3 (4), 1185-1192. PDF

2022

Søgaard, Anders. 2022. Understanding Models Understanding Language. Synthese 200:433. PDF

Miranda, Lester James; Kádár, Ákos; Boyd, Adriane; Van Landeghem, Sofie; Søgaard, Anders; Honnibal, Matthew. 2022. Multi hash embeddings in spaCy. ArXiv:2212.09255. PDF

Due, Jeppe; Pedersen, Marianne; Antonsen, Sussie; Rommedahl, Joen; Agerbo, Esben; Mortensen, Preben Bo; Sørensen, Henrik; Lotz, Jonas; Piqueras, Laura; Fierro, Constanza; Karamolegkou, Antonia; Igel, Christian; Rust, Phillip; Søgaard, Anders; Pedersen, Carsten. 2022. Towards More Comprehensive Nationwide Familial Aggregation Studies in Denmark. Scandinavian Journal of Public Health.

Søgaard, Anders. 2022. Should We Ban English NLP for a Year? Conference on Empirical Methods in Natural Language Processing (EMNLP) 2022. Abu Dhabi. PDF

Jørgensen, Rasmus Kær; Caccavale, Fiammetta; Igel, Christian; Søgaard, Anders. 2022. Are Multilingual Sentiment Models Equally Right for the Right Reasons? EMNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackBoxNLP). Abu Dhabi. PDF

Søgaard, Anders. 2022. Kunstig Intelligens Bagfra [in Danish]. Aarhus Universitetsforlag. Book Audio

Søgaard, Anders. 2022. Shortcomings of Interpretability Taxonomies for Deep Neural Networks. CIKM Workshop on Advances in Interpretable Machine Learning and Artificial Intelligence. Atlanta, GA. PDF

Cabello, Laura; Søgaard, Anders. 2022. Are Pretrained Multilingual Models Equally Fair Across Languages? The 29th International Conference on Computational Linguistics (COLING). Gyeongju, Republic of Korea. PDF

Fierro, Constanza; Cabello Piqueras, Laura; Lotz, Jonas; Rust, Phillip; Rommedahl, Joen; Klok Due, Jeppe; Igel, Chrisitan; Elliott, Desmond; Bøcker Pedersen; Salazar, Israfel; Søgaard, Anders. 2022. Date Recognition in Historical Parish Records. The 18th International Conference on Frontiers of Handwriting Recognition. Hyderabad, India. PDF

Cui, Ruixiang; Hershcovich, Daniel; Søgaard, Anders. 2022. Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarks. North American Chapter of the Association for Computational Linguistics (NAACL). Seattle, WA. PDF

Brandl, Stephanie; Cui, Ruixiang; Søgaard, Anders. 2022. How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns. North American Chapter of the Association for Computational Linguistics (NAACL). Seattle, WA. PDF

Li, Zechen; Søgaard, Anders. 2022. QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning. Findings of the North American Chapter of the Association for Computational Linguistics (NAACL). Seattle, WA. PDF

Petrén Bach Hansen, Victor; Neerkaje, Atula Tejaswi; Sawhney, Ramit; Flek, Lucie; Søgaard, Anders. 2022. The Impact of Differential Privacy on Group Disparity Mitigation. Fourth Workshop on Privacy in Natural Language Processing at NAACL 2022. Seattle, WA. PDF

Brandl, Stephanie; Hershcovich, Daniel; Søgaard, Anders. 2022. Evaluating Deep Taylor Decomposition for Reliability Assessment in the Wild. The International AAAI Conference on Web and Social Media (ICWSM). Atlanta, GA. PDF

Lent, Heather; Ogueji, Kelechi; de Lhoneux, Miryam; Ahia, Orevaoghene and Søgaard, Anders. 2022. What a Creole Wants, What a Creole Needs. The International Conference on Language Resources and Evaluation (LREC). Marseille, France. PDF

Jakobsen, Terne Sasha Thorn; Barrett, Maria; Søgaard, Anders; Dreyer Lassen, David. 2022. The Sensitivity of Annotator Bias to Task Definitions in Argument Mining. The Sixteenth Linguistic Annotation Workshop at LREC 2022. Marseille, France. PDF

de Lhoneux, Miryam; Zhang, Sheng; Søgaard, Anders. 2022. Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning. The 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. PDF

Eberle, Oliver; Brandl, Stephanie; Pilot, Jonas; Søgaard, Anders. 2022. Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze? The 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. PDF

Abdou, Mostafa; Ravishankar, Vinit; Kulmizev, Artur; Søgaard, Anders. 2022. Word Order Does Matter and Shuffled Language Models Know It. The 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. PDF

Chalkidis, Ilias; Pasini, Tommaso; Zhang, Sheng; Tomada, Letizia; Felix Schwemer, Sebastian; Søgaard, Anders. 2022. FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing. The 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. PDF

Hershcovich, Daniel; Frank, Stella; Lent, Heather; de Lhoneux, Miryam; Abdou, Mostafa; Brandl, Stephanie; Bugliarello, Emanuele; Piqueras, Laura Cabello; Chalkidis, Ilias; Cui, Ruixiang; Fierro, Constanza; Margatina, Katerina; Rust, Phillip; Søgaard, Anders. 2022. Challenges and Strategies in Cross-Cultural NLP. The 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. PDF

Ruder, Sebastian; Vulic, Ivan; Søgaard, Anders. 2022. Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold. Findings of The 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. PDF

Fierro; Constanza; Søgaard, Anders. 2022. Factual Consistency of Multilingual Pretrained Language Models. Findings of The 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. PDF

Chalkidis, Ilias; Søgaard, Anders. 2022. Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting. Findings of The 60th Annual Meeting of the Association for Computational Linguistics (ACL). Dublin, Ireland. PDF

Lent, Heather; Bugliarello, Emanuele; Søgaard, Anders. 2022. Ancestor-to-Creole Transfer is Not a Walk in the Park. ACL Workshop on Insights from Negative Results in NLP. Dublin, Ireland. PDF

Noe, Frederik; Herskind, Rasmus; Søgaard, Anders. 2022. Exploring the Unfairness of DP-SGD Across Settings. The Third AAAI Workshop on Privacy-Preserving Artificial Intelligence. Vancouver, Canada. PDF

2021

Søgaard, Anders. 2021. Explainable Natural Language Processing. Morgan & Claypool. PDF Review

Ravishankar, Vinit; Søgaard, Anders. 2021. The Impact of Positional Encodings on Multilingual Compression. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021. Punta Cana, Dominican Republic. PDF

Kementchedjhieva, Yova; Søgaard, Anders. 2021. Dynamic Forecasting of Conversation Derailment. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021. Punta Cana, Dominican Republic. PDF

Zhang, Sheng; Zhang, Xin; Zhang, Weiming; Søgaard, Anders. 2021. Sociolectal Analysis of Pretrained Language Models. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021. Punta Cana, Dominican Republic. PDF

Søgaard, Anders. 2021. Locke’s Holiday: Belief Bias in Machine Reading. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021. Punta Cana, Dominican Republic. PDF

Christiansen, Jonathan; Gammelgaard, Mathias; Søgaard, Anders. 2021. The Effect of Round-Trip Translation on Fairness in Document Classification. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2021. Punta Cana, Dominican Republic. PDF

Abdou, Mostafa; Kulmizev, Artur; Hershcovich, Daniel; Frank, Stella; Pavlick, Ellie; Søgaard, Anders. 2021. Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color. Conference on Computational Natural Language Learning (CoNLL). Punta Cana, Dominican Republic. PDF

Hartmann, Mareike; de Lhoneux, Miryam; Hershcovich, Daniel; Kementchedjhieva, Yova; Nielsen, Lukas; Qiu, Chen; Søgaard, Anders. 2021. A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs. Conference on Computational Natural Language Learning (CoNLL). Punta Cana, Dominican Republic. PDF

Lent, Heather; Bugliarello, Emanuele; de Lhoneux, Miryam; Qiu, Chen; Søgaard, Anders. 2021. On Language Models for Creoles. Conference on Computational Natural Language Learning (CoNLL). Punta Cana, Dominican Republic. PDF

Jørgensen, Anna Katrine; Søgaard, Anders. 2021. Evaluation of Summarization Systems across Gender, Age, and Race. EMNLP Workshop on New Frontiers in Summarization. Punta Cana, Dominican Republic. PDF

Lent, Heather; Søgaard, Anders. 2021. Common Sense Bias in Semantic Role Labeling. EMNLP Workshop on Noisy User-generated Text (W-NUT). Punta Cana, Dominican Republic. PDF

Liétard, Bastien; Abdou, Mostafa; Søgaard, Anders. 2021. Do Language Models Know the Way to Rome? EMNLP Workshop on BlackBoxNLP. Punta Cana, Dominican Republic. PDF

Bassani, Riccardo; Søgaard, Anders; Deoskar, Tejaswini. 2021. Clustering Monolingual Vocabularies to Improve Cross-Lingual Generalization. EMNLP Workshop on Multilingual Representation Learning. Punta Cana, Dominican Republic. PDF

Barrett, Maria; Lam, Hieu Trong; Wu, Martin; Lacroix, Ophélie; Plank, Barbara; Søgaard, Anders. 2021. Resources and Evaluations for Danish Entity Resolution. EMNLP Workshop on Computational Models of Reference, Anaphora and Coreference. Punta Cana, Dominican Republic. PDF

Jakobsen, Terne Sasha; Barrett, Maria; Søgaard, Anders. 2021. Spurious Correlations in Cross-Topic Argument Mining. The 10th Joint Conference on Lexical and Computational Semantics (*SEM). Virtual conference. PDF

Karthikeyan, K; Søgaard, Anders. 2021. Revisiting Methods for Finding Influential Examples. ArXiv:2111.04683. ArXiv

Kementchedjhieva, Yova; Anderson, Mark; Søgaard, Anders. 2021. John praised Mary because he? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs. Findings of The 59th Annual Meeting of the Association for Computational Linguistics (ACL). Virtual conference. PDF

Anderson, Mark; Søgaard, Anders; Gomez-Rodriguez, Carlos. 2021. Replicating and Extending “Because Their Treebanks Leak”: Graph Isomorphism, Covariants, and Parser Performance. The 59th Annual Meeting of the Association for Computational Linguistics (ACL). Virtual conference. PDF

Gonzalez, Ana Valeria; Rogers, Anna; Søgaard, Anders. 2021. On the Interaction of Belief Bias and Explanations. Findings of The 59th Annual Meeting of the Association for Computational Linguistics (ACL). Virtual conference. PDF

Petrén Bach Hansen, Victor; Søgaard, Anders. 2021. Is the Lottery Fair? Evaluating Winning Tickets Across Demographics. Findings of The 59th Annual Meeting of the Association for Computational Linguistics (ACL). Virtual conference. PDF

Ponti, Edoardo; Aralikatte, Rahul; Shrivastava, Disha; Reddy, Siva; Søgaard, Anders. 2021. Minimax and Neyman–Pearson Meta-Learning for Outlier Languages. Findings of The 59th Annual Meeting of the Association for Computational Linguistics (ACL). Virtual conference. PDF

Petrén Bach Hansen, Victor; Søgaard, Anders. 2021. Guideline Bias in Wizard-of-Oz Dialogues. ACL Workshop on Benchmarking. Virtual conference. PDF

Aralikatte, Rahul; de Lhoneux, Miryam; Kunchukuttan, Anoop; Søgaard, Anders. 2021. Itihasa: A large-scale corpus for Sanskrit to English translation. ACL Workshop on Asian Translation. Virtual conference. PDF

Aralikatte, Rahul; Bello, Hector Ricardo Murrieta; de Lhoneux, Miryam; Hershcovich, Daniel; Bollmann, Marcel; Søgaard, Anders. 2021. How far can we get with one GPU in 100 hours? CoAStaL at the MultiIndicMT Shared Task. ACL Workshop on Asian Translation. Virtual conference. PDF

Søgaard, Anders; Ebert, Sebastian; Bastings, Jasmijn; Filippova, Katja. 2021. We Need To Talk About Random Splits. The 16th conference of the European Chapter of the Association for Computational Linguistics (EACL). Virtual conference. Received Honorable Mention. ArXiv Google PDF

Aralikatte, Rahul; Lamm, Matthew; Hardt, Daniel; Søgaard, Anders. 2021. Ellipsis Resolution as Question Answering: An Evaluation. The 16th conference of the European Chapter of the Association for Computational Linguistics (EACL). Virtual conference. ArXiv PDF

Bollmann, Marcel; Søgaard, Anders. 2021. Error Analysis and the Role of Morphology. The 16th conference of the European Chapter of the Association for Computational Linguistics (EACL). Virtual conference. Received Best Long Paper Award. PDF

Kulmizev, Artur; Ravishankar, Vinit; Abdou, Mostafa; Søgaard, Anders; Nivre, Joakim. 2021. Attention Can Reflect Syntactic Structure (If You Let It). The 16th conference of the European Chapter of the Association for Computational Linguistics (EACL). Virtual conference. ArXiv PDF

Hartmann, Mareike; Søgaard, Anders. 2021. Multilingual Negation Scope Resolution for Clinical Text. The 12th International Workshop on Health Text Mining and Information Analysis, EACL 2021. Virtual conference. PDF

Garneau, Nicolas; Hartmann, Mareike; Sandholm, Anders; Ruder, Sebastian; Vulic, Ivan; Søgaard, Anders. 2021. Analogy Training Multilingual Encoders. The 35th AAAI Conference on Artificial Intelligence (AAAI). Virtual conference. PDF

Aralikatte, Rahul; Abdou, Mostafa; Lent, Heather; Hershcovich, Daniel; Søgaard, Anders. 2021. Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards. The 35th AAAI Conference on Artificial Intelligence (AAAI). Virtual conference. ArXiv

Bollmann, Marcel; Aralikatte, Rahul; Bello Héctor Murrieta; Hershcovich, Daniel; de Lhoneux, Miryam; Søgaard, Anders. 2021. Moses and the Character-Based Random Babbling Baseline: CoAStaL at AmericasNLP 2021 Shared Task. NAACL Workshop on NLP for Indigenous Languages of the Americas. Virtual Conference.

Qiu, Chen; Zhou, Guangyou; Cai; Zhihua; Søgaard, Anders. 2021. A Global-Local Attentive Relation Detection Model for Knowledge Base Question Answering. IEEE Transactions on Artificial Intelligence. Early Access

Abdou, Mostafa; Gonzalez, Ana Valeria; Toneva, Mariya; Hershcovich, Daniel; Søgaard, Anders. 2021. Does injecting linguistic structure into language models lead to better alignment with brain recordings? ArXiv

2020

Gonzalez, Ana Valeria; Søgaard, Anders. 2020. The Reverse Turing Test for Evaluating Interpretability Methods on Unknown Tasks. NeurIPS Workshop on Human And Machine in-the-Loop Evaluation and Learning Strategies. Virtual conference. PDF

Gonzalez, Ana Valeria; Barrett, Maria; Hvingelby, Rasmus; Webster, Kellie; Søgaard, Anders. 2020. Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. Punta Cana, Dominican Republic. PDF

Søgaard, Anders. 2020. Some Languages Seem Easier to Parse Because Their Treebanks Leak. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. Punta Cana, Dominican Republic. PDF Erratum: The explained variance numbers are unstable; will post new results on ArXiv very soon.

Vulic, Ivan; Ruder, Sebastian; Søgaard, Anders. 2020. Are All Good Word Vector Spaces Isomorphic? Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. Punta Cana, Dominican Republic. PDF ArXiv

Flachs, Simon; Lacroix, Ophelie; Yannakoudakis, Helen; Rei, Marek; Søgaard, Anders. 2020. Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. Punta Cana, Dominican Republic. PDF

Søgaard, Anders. 2020. Neural Speed Reading Audited. Findings of Conference on Empirical Methods in Natural Language Processing (EMNLP) 2020. Punta Cana, Dominican Republic. PDF

Zhang, Sheng; Xhang, Xin; Zhang, Weiming; Søgaard, Anders. 2020. Worst-Case-Aware Curriculum Learning for Zero and Few Shot Transfer. ArXiv

Borgholt, Lasse; Havtorn, Jacob; Agic, Zeljko; Søgaard, Anders; Maaløe, Lars; Igel, Christian. 2020. Do End-to-End Speech Recognition Models Care About Context? Interspeech 2020. Shanghai, China. PDF

Abdou, Mostafa; Ravishankar, Vinit; Barrett, Maria; Belinkov, Yonatan; Elliott, Desmond; Søgaard, Anders. 2020. The Sensitivity of Language Models and Humans to Winograd Schema Perturbations. The 57th Annual Meeting of the Association for Computational Linguistics (ACL). Seattle, Washington. PDF

Petrén Bach Hansen, Victor; Søgaard, Anders. 2020. What Do You Mean ‘Why?’: Resolving Sluices in Conversations. The 34th AAAI Conference on Artificial Intelligence (AAAI). New York, New York. PDF

Kann, Katharina; Lacroix, Ophelie; Søgaard, Anders. 2020. Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages. The 34th AAAI Conference on Artificial Intelligence (AAAI). New York, New York. ArXiv

Vilares, David; Strzyz, Michalina; Søgaard, Anders; Gomez-Rodriquez, Carlos. 2020. Parsing as pretraining. The 34th AAAI Conference on Artificial Intelligence (AAAI). New York, New York. ArXiv GitHub

Sas, Cezar; Beloucif, Meriem; Søgaard, Anders. 2020. WikiBank: Using Wikidata to Improve Multilingual Frame-Semantic Parsing. The 12th International Conference on Language Resources and Evaluation (LREC). Marseille, France. PDF

Aralikatte, Rahul; Søgaard, Anders. 2020. Model-based annotation of coreference. The 12th International Conference on Language Resources and Evaluation (LREC). Marseille, France. PDF

Hvingelby, Rasmus; Paul, Amalie Brogaard; Barrett, Maria; Rosted, Christina; Lidegaard, Lasse Malm; Søgaard, Anders. 2020. DaNE: A Named Entity Resource for Danish. The 12th International Conference on Language Resources and Evaluation (LREC). Marseille, France. PDF

2019

Hartmann, Mareike; Kementchedjhieva, Yova; Søgaard. Anders. 2019. Comparing Unsupervised Word Translation Methods Step by Step. The 33rd Conference on Neural Information Processing Systems (NeurIPS 2019). Vancouver, Canada. PDF

Bingel, Joachim; Petrén Bach Hansen, Victor; Gonzalez, Ana Valeria; Budzianowski, Pavel; Augenstein, Isabelle; Søgaard, Anders. 2019. Domain Transfer in Dialogue Systems without Turn-Level Supervision. The 3rd NeurIPS workshop on Conversational AI: Today’s Practice and Tomorrow’s Potential. Vancouver, Canada. ArXiv

Gonzalez, Ana Valeria; Augenstein, Isabelle; Søgaard, Anders. 2019. Retrieval-based goal-directed dialogue generation. The 3rd NeurIPS workshop on Conversational AI: Today’s Practice and Tomorrow’s Potential. Vancouver, Canada. ArXiv

Aralikatte, Rahul; Lent, Heather; Gonzalez, Ana Valeria; Herschcovich, Daniel; Qiu, Chen; Sandholm, Anders; Ringgaard, Michael; Søgaard, Anders. Rewarding Coreference Resolvers for Being Consistent with World Knowledge. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019. Hong Kong, China. ArXiv

Kementchedjhieva, Yova; Hartmann, Mareike; Søgaard, Anders. 2019. Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary Induction. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019. Hong Kong, China. PDF

Barrett, Maria; Kementchedjhieva, Yova; Elazar, Yanai; Elliott, Desmond; Søgaard, Anders. 2019. Adversarial Removal of Demographic Attributes Revisited. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019. Hong Kong, China. PDF

Abdou, Mostafa; Kulmizev, Artur; Hill, Felix; Low, Daniel; Søgaard, Anders. 2019. Higher-order Comparisons of Sentence Encoder Representations. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019. Hong Kong, China. PDF ArXiv

Vania, Clara; Kementchedjhieva, Yova; Søgaard, Anders; Lopez, Adam. 2019. A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2019. Hong Kong, China. ArXiv

Abdou, Mostafa; Sas, Cezar; Aralikatte, Rahul; Augenstein, Isabelle; Søgaard, Anders. 2019. X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension. Workshop on Deep Learning Approaches for Low-Resource NLP, EMNLP 2019. ArXiv

Bollmann, Marcel; Korchagina, Natalia; Søgaard, Anders. 2019. Few-Shot and Zero-Shot Learning for Historical Text Normalization. Workshop on Deep Learning Approaches for Low-Resource NLP, EMNLP 2019. PDF

Beloucif, Meriem; Gonzalez, Ana Valeria; Bollmann, Marcel; Søgaard, Anders. 2019. Naive regularizers for low-resource neural machine translation. Recent Advances in Natural Language Processing 2019. Borovets, Bulgaria. PDF

Søgaard, Anders; Vulic, Ivan; Ruder, Sebastian; Faruqui, Manaal. 2019. Cross-lingual word embeddings. Morgan & Claypool. PDF

Ruder, Sebastian; Vulic, Ivan; Søgaard, Anders. 2019. A survey of cross-lingual word embedding models. Journal of Artificial Intelligence Research (JAIR) 65. PDF Arxiv

Kurita, Shuhei; Søgaard, Anders. 2019. Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies. The 56th Annual Meeting of the Association for Computational Linguistics (ACL). Florence, Italy. PDF

Flachs, Simon; Bollmann, Marcel; Søgaard, Anders. 2019. Historical Text Normalization with Delayed Rewards. The 56th Annual Meeting of the Association for Computational Linguistics (ACL). Florence, Italy. PDF

Flachs, Simon; Lacroix, Ophélie; Søgaard, Anders. 2019. Noisy channel for low resource grammatical error correction. 14th Workshop on Innovative Use of NLP for Building Educational Applications, ACL 2019. Florence, Italy. PDF

Flachs, Simon; Lacroix, Ophélie; Rei, Marek; Yannakoudakis, Helen; Søgaard, Anders. 2019. A simple and robust approach to detecting subject-verb agreement errors. North American Chapter of the Association for Computational Linguistics (NAACL). Minneapolis, Minnesota. PDF

Hartmann, Mareike; Jansen, Tallulah; Augenstein, Isabelle; Søgaard, Anders. 2019. Issue Framing in Online Discussion Fora. North American Chapter of the Association for Computational Linguistics (NAACL). Minneapolis, Minnesota. PDF

Vilares, David; Abdou, Mostafa; Søgaard, Anders. 2019. Better, faster, stronger sequence tagging constituent parsers. North American Chapter of the Association for Computational Linguistics (NAACL). Minneapolis, Minnesota. PDF

Gonzalez-Garduno, Ana Valeria; Petrén Bach Hansen, Victor; Bingel, Joachim; Søgaard, Anders. 2019. CoAStaL at SemEval-2019 Task 3: Affect Classification in Dialogue using Attentive BiLSTMs. The 13th International Workshop on Semantic Evaluation (SemEval). Minneapolis, Minnesota. PDF

Rei, Marek; Søgaard, Anders. 2019. Jointly learning to label sentences and tokens. The 33rd AAAI Conference on Artificial Intelligence (AAAI). Honolulu, Hawaii. Arxiv

Ruder, Sebastian; Bingel, Joachim, Augenstein, Isabelle; Søgaard, Anders. 2019. Latent multi-task architecture learning. The 33rd AAAI Conference on Artificial Intelligence (AAAI). Honolulu, Hawaii. Arxiv

Caccavale, Fiammetta; Søgaard, Anders. 2019. Predicting concrete and abstract entities in modern poetry. The 33rd AAAI Conference on Artificial Intelligence (AAAI). Honolulu, Hawaii. PDF

2018

Hartmann, Mareike; Kementchedjhieva, Yova; Søgaard, Anders. 2018. Why is unsupervised alignment of English embeddings from different algorithms so hard? Conference on Empirical Methods in Natural Language Processing (EMNLP) 2018. Brussels, Belgium. PDF

Ruder, Sebastian; Cotterell, Ryan; Kementchedjhieva, Yova; Søgaard, Anders. 2018. A discriminative latent-variable model for bilingual lexicon induction. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2018. Brussels, Belgium. PDF

de Lhoneux, Miryam; Bjerva, Johannes; Augenstein, Isabelle; Søgaard, Anders. 2018. Parameter sharing between dependency parsers for related languages. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2018. Brussels, Belgium. PDF

Gonzalez-Garduno, Ana Valeria; Augenstein, Isabelle; Søgaard, Anders. 2018. A strong baseline for question relevancy ranking. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2018. Brussels, Belgium. PDF

Kementchedjhieva, Yova; Ruder, Sebastian; Cotterell, Ryan; Søgaard, Anders. 2018. Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction. Conference on Computational Natural Language Learning (CoNLL). Brussels, Belgium. PDF

Barrett, Maria; Bingel, Joachim; Hollenstein, Nora; Rei, Marek; Søgaard, Anders. 2018. Sequence classification with human attention. Conference on Computational Natural Language Learning (CoNLL). Brussels, Belgium. Received Best Paper Award. PDF

Rønning, Ola; Hardt, Daniel; Søgaard, Anders. 2018. Linguistic representations in multi-task neural networks for ellipsis resolution. EMNLP Workshop on Analyzing and interpreting neural networks for NLP. Brussels, Belgium. PDF

Kerinec, Emma; Braud, Chloe; Søgaard, Anders. 2018. When does deep multi-task learning work for loosely related document classification tasks? EMNLP Workshop on Analyzing and interpreting neural networks for NLP. Brussels, Belgium. PDF

Søgaard, Anders; de Lhoneux, Miryam; Augenstein, Isabelle. 2018. Nightmare at test time: How punctuation prevents parsers from generalizing. EMNLP Workshop on Analyzing and interpreting neural networks for NLP. Brussels, Belgium. PDF

Lukes, Jan; Søgaard, Anders. 2018. Sentiment analysis under temporal shift. EMNLP Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA). Brussels, Belgium. PDF

Petrén Bach Hansen, Victor; Søgaard, Anders. 2018. Learning language-independent representations of verbs and adjectives from multimodal retrieval. SITIS Workshop on Multimedia Information Retrieval and Applications. Las Palmas, Gran Canaria. Proceedings

Søgaard, Anders; Ruder, Sebastian; Vulic, Ivan. 2018. On the limitations of unsupervised bilingual dictionary induction. The 56th Annual Meeting of the Association for Computational Linguistics (ACL). Melbourne, Australia. PDF

Bollmann, Marcel; Bingel, Joachim; Søgaard, Anders. 2018. Multi-task learning for historical text normalization: Size matters. Deep Learning Approaches for Low Resource Natural Language Processing (ACL). Melbourne, Australia. PDF

Kann, Katharina; Bjerva, Johannes; Augenstein, Isabelle; Plank, Barbara; Søgaard, Anders. 2018. Character-level Supervision for Low-resource POS Tagging. Deep Learning Approaches for Low Resource Natural Language Processing (ACL). Melbourne, Australia. PDF

Hartmann, Mareike; Søgaard, Anders. 2018. Limitations of cross-lingual learning from image search. 3rd Workshop on Representation Learning for NLP (ACL). Melbourne, Australia. PDF Data

Bingel, Joachim; Paetzold, Gustavo; Søgaard, Anders. 2018. Lexi: A tool for adaptive, personalized text simplification. The 27th International Conference on Computational Linguistics (COLING), Demo Session. Santa Fe, New Mexico. PDF Code

Augenstein, Isabelle; Ruder, Sebastian; Søgaard, Anders. 2018. Multi-task learning of pairwise sequence classification tasks over disparate label spaces. North American Chapter of the Association for Computational Linguistics (NAACL). New Orleans, Louisiana. PDF Arxiv Code

Rønning, Ola; Hardt, Daniel; Søgaard, Anders. 2018. Sluice resolution without hand-crafted features over brittle syntax. North American Chapter of the Association for Computational Linguistics (NAACL). New Orleans, Louisiana. PDF

Barrett, Maria; Frermann, Lea; Gonzalez-Garduno, Ana Valeria; Søgaard, Anders. 2018. Unsupervised induction of linguistic categories with records of reading, speaking, and writing. North American Chapter of the Association for Computational Linguistics (NAACL). New Orleans, Louisiana. PDF

Rei, Marek; Søgaard, Anders. 2018. Zero-shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens. North American Chapter of the Association for Computational Linguistics (NAACL). New Orleans, Louisiana. PDF

Gonzalez-Garduno, Ana Valeria; Søgaard, Anders. 2018. Learning to predict readability using eye-movement data from natives and learners. The 32nd AAAI Conference on Artificial Intelligence (AAAI). New Orleans, Louisiana. PDF

Søgaard, Anders. 2018. What I think when I think about treebanks. 16th International Workshop on Treebanks and Linguistic Theories. Prague, Czech. PDF

Pedersen, Bolette; Nimb, Sanni; Søgaard, Anders; Hartmann, Mareike; Olsen, Sussi. 2018. A Danish FrameNet Lexicon and an Annotated Corpus Used for Training and Evaluating a Semantic Frame Classifier. Language Resources and Evaluation Conference (LREC) 2018. Miyazaki, Japan. PDF

2017

Felbo, Bjarke; Mislove, Alan; Søgaard, Anders; Rahwan, Iyan; Lehmann, Sune. 2017. Using millions of emoji occurrences to pretrain any-domain models for detecting emotion, sentiment, and sarcasm. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2017. Copenhagen, Denmark. PDF

Braud, Chloe; Lacroix, Ophelie; Søgaard, Anders. 2017. Does syntax help discourse segmentation? Not so much. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2017. Copenhagen, Denmark. PDF

Gonzalez-Garduno, Ana; Søgaard, Anders. 2017. Using gaze to predict text readability. 12th Workshop on Innovative Use of NLP for Building Educational Applications, EMNLP 2017. Copenhagen, Denmark. PDF

Braud, Chloe; Søgaard, Anders. 2017. Is writing style predictive of scientific fraud? Workshop on Stylistic Variation, EMNLP 2017. Copenhagen, Denmark. PDF

Salehi, Bahar; Søgaard, Anders. 2017. Evaluating hypotheses in geolocation on a very large sample of Twitter. Workshop on Noisy User-generated Text (W-NUT), EMNLP 2017. Copenhagen, Denmark. PDF

Salehi, Bahar; Hovy, Dirk; Hovy, Eduard; Søgaard, Anders. 2017. Huntsville, hospitals, and hockey teams: Names can reveal your location. Workshop on Noisy User-generated Text (W-NUT), EMNLP 2017. Copenhagen, Denmark. PDF

Søgaard, Anders. 2017. Using hyperlinks to train multilingual partial parsers. The 15th International Conference on Parsing Technologies (IWPT). Pisa, Italy. PDF

Ruder, Sebastian; Bingel, Joachim; Augenstein, Isabelle; Søgaard, Anders. 2017. Learning what to share between loosely related tasks. Arxiv

Hartmann, Mareike; Søgaard, Anders. 2017. Limitations of cross-lingual learning from image search. Arxiv

Bollmann, Marcel; Bingel, Joachim; Søgaard, Anders. 2017. Learning attention for historical text normalization by learning to pronounce. The 55th Annual Meeting of the Association for Computational Linguistics (ACL). Vancouver, Canada. PDF

Braud, Chloe; Lacroix, Ophelie; Søgaard, Anders. 2017. Cross-lingual and cross-domain discourse segmentation of entire documents. The 55th Annual Meeting of the Association for Computational Linguistics (ACL). Vancouver, Canada. PDF

Augenstein, Isabelle; Søgaard, Anders. 2017. Multi-task learning of keyphrase boundary classification. The 55th Annual Meeting of the Association for Computational Linguistics (ACL). Vancouver, Canada. PDF

Felbo, Bjarke; Mislove, Allan; Søgaard, Anders; Rahwan, Iyad; Lehmann, Sune. 2017. Using millions of emoji occurrences to pretrain any-domain models for detecting emotion, sentiment and sarcasm. 2nd Workshop on Representation Learning for NLP, ACL 2017. Vancouver, Canada.

Nimb, Sanni; Olsen, Sussi; Pedersen, Bolette; Braasch, Anna; Sørensen, Nicolai; Søgaard, Anders. 2017. From thesaurus to framenet and annotated text. Electronic Lexicography in the 21st Century (eLex). Leiden, the Netherlands. PDF

Gonzalez-Garduño, Ana Valeria; Søgaard, Anders. 2017. Using gaze data to evaluate text readability: a multi-task learning approach. 19th European Conference on Eye Movements (ECEM). Wuppertal, Germany.

Søgaard, Anders. 2017. Spikes as regularizers. European Symposium on Artificial Neural Networks, Computational Intelligence, and Machine Learning. Brugge, Belgium. Arxiv

Bingel, Joachim; Søgaard, Anders. 2017. Identifying beneficial task relations for multi-task learning in deep neural networks. The 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Valencia, Spain. PDF

Agic, Zeljko; Plank, Barbara; Søgaard, Anders. 2017. Cross-lingual tagger evaluation without test data. The 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Valencia, Spain. PDF

Schlichtkrull, Michael; Søgaard, Anders. 2017. Cross-lingual dependency parsing with late decoding for truly low-resource parsing. The 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Valencia, Spain. PDF

Braud, Chloe; Coavoux, Maximin; Søgaard, Anders. 2017. Cross-lingual RST discourse parsing. The 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Valencia, Spain. PDF

Levy, Omer; Søgaard, Anders; Goldberg, Yoav. 2017. A strong baseline for learning cross-lingual word embeddings from sentence alignments. The 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Valencia, Spain. PDF

Alonso, Hector Martinez; Plank, Barbara; Søgaard, Anders. 2017. Parsing universal dependencies without training. The 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Valencia, Spain. PDF

2016

Braud, Chloe; Plank, Barbara; Søgaard, Anders. 2016. Multi-view and multi-task training of RST discourse parsers. The 26th International Conference on Computational Linguistics (COLING). Osaka, Japan. PDF

Bollmann, Marcel; Søgaard, Anders. 2016. Improving historical spelling normalization with bi-directional LSTMs and multi-task learning. The 26th International Conference on Computational Linguistics (COLING). Osaka, Japan. PDF

Barrett, Maria; Keller, Frank; Søgaard, Anders. 2016. Cross-lingual transfer of correlations between parts of speech and gaze features. The 26th International Conference on Computational Linguistics (COLING). Osaka, Japan. PDF

Søgaard, Anders. 2016. Spikes as regularizers. NIPS Workshop on Computing with Spikes. Barcelona, Spain. Arxiv

Agic, Zeljko; Johannsen, Anders; Plank, Barbara; Martinez, Hector; Schluter, Natalie; Søgaard, Anders. 2016. Multi-lingual projection for parsing truly low resource languages. Transactions of the Association for Computational Linguistics (TACL) 4: 301-312. PDF

Søgaard, Anders. 2016. Evaluating word embeddings with fMRI and eye-tracking. RepEval, The 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. Nominated for Best Paper Award. PDF

Bingel, Joachim; Barrett, Maria; Søgaard, Anders. 2016. Extracting token-level signals of syntactic processing from fMRI - with an application to POS induction. The 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. PDF

Søgaard, Anders; Goldberg, Yoav. 2016. Deep multi-task learning with low level tasks supervised at lower layers. The 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. PDF

Plank, Barbara; Søgaard, Anders; Goldberg, Yoav. 2016. Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss. The 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. PDF Code

Bingel, Joachim; Søgaard, Anders. 2016. Text simplification as tree labeling. The 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. PDF

Johannsen, Anders; Agic, Zeljko; Søgaard, Anders. 2016. Joint part-of-speech and dependency projection from multiple sources. The 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. PDF

Barrett, Maria; Bingel, Joachim; Keller, Frank; Søgaard, Anders. 2016. Weakly supervised part-of-speech tagging using eye-tracking data. The 54th Annual Meeting of the Association for Computational Linguistics (ACL). Berlin, Germany. PDF

Klerke, Sigrid; Goldberg, Yoav; Søgaard, Anders. 2016. Improving sentence compression by learning to predict gaze. North American Chapter of the Association for Computational Linguistics (NAACL). San Diego, CA. Received Best Short Paper Award. PDF

Jørgensen, Anna; Hovy, Dirk; Søgaard, Anders. 2016. Learning a POS tagger for AAVE-like language. North American Chapter of the Association for Computational Linguistics (NAACL). San Diego, CA. PDF

Pedersen, Bolette; Braasch, Anna; Johannsen, Anders; Alonso, Hector Martinez; Nimb, Sanni; Olsen, Sussi; Søgaard, Anders; Sørensen, Nicolai Hartvig. 2016. The SemDaX corpus - sense annotations with scalable sense inventories. Language Resources and Evaluation Conference (LREC) 2016. Portoroz, Slovenia. PDF

Jørgensen, Anna; Søgaard, Anders. 2016. A test suite for evaluating POS taggers across varieties of English. WWW Workshop on NLP for Informal Text. Montreal, Canada. Link

Søgaard, Anders. 2016. Biases we live by. Nordisk Tidsskrift for Informationsvidenskab og Kulturformidling 5(1): 31-35. PDF

2015

Søgaard, Anders. 2015. Empirical Gaussian priors for cross-lingual transfer learning. NIPS Workshop on Transfer and Multi-task Learning. Montreal, Canada. ArXiv

Barrett, Maria; Agic, Zeljko; Søgaard, Anders. 2015. The Dundee Treebank. Treebanks and Linguistic Theories 14. Warsaw, Poland. PDF

Johannsen, Anders; Martinez, Hector; Søgaard, Anders. 2015. Any-language frame semantic parsing. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2015. Lisbon, Portugal. PDF

Klerke, Sigrid; Barrett, Maria; Castilho, Sheila; Søgaard, Anders. 2015. Reading metrics for estimating task efficiency with MT output. EMNLP Workshop on Cognitive Aspects of Computational Language Learning. Lisbon, Portugal. PDF

Barrett, Maria; Søgaard, Anders. 2015. Using reading behavior to predict grammatical functions. EMNLP Workshop on Cognitive Aspects of Computational Language Learning. Lisbon, Portugal. PDF

Søgaard, Anders; Agic, Zeljko; Martinez, Hector; Plank, Barbara; Bohnet, Bernd; Johannsen, Anders. 2015. Inverted indexing for cross-lingual NLP. The 53rd Annual Meeting of the Association for Computational Linguistics (ACL). Beijing, China. PDF

Hovy, Dirk; Søgaard, Anders. 2015. Tagging performance correlates with author age. The 53rd Annual Meeting of the Association for Computational Linguistics (ACL). Beijing, China. PDF

Schluter, Natalie; Søgaard, Anders. 2015. Unsupervised extractive summarization via coverage maximization with syntactic and semantic concepts. The 53rd Annual Meeting of the Association for Computational Linguistics (ACL). Beijing, China. PDF

Agic, Zeljko; Hovy, Dirk; Søgaard, Anders. 2015. If all you have is a bit of the Bible: Learning POS taggers for truly low-resource languages. The 53rd Annual Meeting of the Association for Computational Linguistics (ACL). Beijing, China. PDF

Johannsen, Anders; Hovy, Dirk; Søgaard, Anders. 2015. Cross-lingual syntactic variation over age and gender. The 19th Conference on Computational Natural Language Learning (CoNLL). Beijing, China. PDF

Plank, Barbara; Martinez Alonso, Hector; Agic, Zeljko; Merkler, Danijela; Søgaard, Anders. 2015. Do dependency parsing metrics correlate with human judgments? The 19th Conference on Computational Natural Language Learning (CoNLL). Beijing, China. PDF

Barrett, Maria; Søgaard, Anders. 2015. Reading behavior predicts syntactic categories. The 19th Conference on Computational Natural Language Learning (CoNLL). Beijing, China. PDF

Wullf, Julie; Søgaard, Anders. 2015. Learning finite state word representations for unsupervised Twitter adaptation of POS taggers. ACL 2015 Workshop on Noisy User-generated Text (W-NUT). Beijing, China. PDF

Jørgensen, Anna Katrine; Hovy, Dirk; Søgaard, Anders. 2015. Challenges of studying and processing dialects in social media. ACL 2015 Workshop on Noisy User-generated Text (W-NUT). Beijing, China. Received Best Paper Award. PDF

Søgaard, Anders. 2015. Where is language? ACL 2015 Workshop on Noisy User-generated Text (W-NUT). Beijing, China.

Martinez Alonso, Hector; Plank, Barbara; Skjærholt, Arne; Søgaard, Anders. 2015. Learning to parse with IAA-weighted loss. North American Chapter of the Association for Computational Linguistics (NAACL). Denver, CO. PDF

Gouws, Stephan; Søgaard, Anders. 2015. Simple task-specific bilingual word embeddings. North American Chapter of the Association for Computational Linguistics (NAACL). Denver, CO. PDF

Hovy, Dirk; Plank, Barbara; Martinez Alonso, Hector; Søgaard, Anders. 2015. Mining for unambiguous instances to adapt POS taggers to new domains. North American Chapter of the Association for Computational Linguistics (NAACL). Denver, CO. PDF

Plank, Barbara; Martinez Alonso, Hector; Søgaard, Anders. 2015. Non-canonical language is not harder to annotate than canonical language. The 9th Linguistic Annotation Workshop (LAW IX), NAACL. Denver, CO. PDF

Hovy, Dirk; Johannsen, Anders; Søgaard, Anders. 2015. User review sites as a resource for large-scale sociolinguistic studies. The 24th International World Wide Web Conference (WWW). Florence, Italy. PDF

Martinez, Hector; Plank, Barbara; Johannsen, Anders; Søgaard, Anders. 2015. Active learning for sense annotation. The 20th Nordic Conference on Computational Linguistics (NODALIDA). Vilnius, Lithuania. PDF

Martinez, Hector; Johannsen, Anders; Olsen, Sussi; Nimb, Sanni; Sørensen, Nicolai Hartvig; Braasch, Anna; Søgaard, Anders; Pedersen, Bolette Sandford. 2015. Supersense tagging for Danish. The 20th Nordic Conference on Computational Linguistics (NODALIDA). Vilnius, Lithuania. PDF

Søgaard, Anders, Plank, Barbara; Martinez, Hector. 2015. Using frame semantics for knowledge extraction from Twitter. The 29th Conference on Artificial Intelligence (AAAI). Austin, TX. PDF

Barrett, Maria; Søgaard, Anders. 2015. Modeling eye movements when reading microblogs. The 20th AAAI/SIGAI Doctoral Consortium, collocated with The 29th Conference on Artificial Intelligence (AAAI). Austin, TX.

2014

Plank, Barbara; Johannsen, Anders; Søgaard, Anders. 2014. Importance weighting and unsupervised domain adaptation of POS taggers: a negative result. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2014. Doha, Qatar. PDF

Plank, Barbara; Hovy, Dirk; McDonald, Ryan; Søgaard, Anders. 2014. Adapting taggers to Twitter using not-so-distant supervision. The 25th International Conference on Computational Linguistics (COLING). Dublin, Ireland. PDF

Søgaard, Anders; Plank, Barbara; Hovy, Dirk. 2014. Selection bias, label bias, and bias in ground truth (tutorial). The 25th International Conference on Computational Linguistics (COLING). Dublin, Ireland.

Johannsen, Anders; Hovy, Dirk; Martinez, Hector; Søgaard, Anders. 2014. More or less supervised supersense tagging of Twitter. The 3rd Joint Conference on Lexical and Computational Semantics (*SEM). Dublin, Ireland. Received Best Paper Award. PDF

Søgaard, Anders; Johannsen, Anders; Plank, Barbara; Hovy, Dirk; Martinez, Hector. 2014. What is in a p-value in NLP? The 18th Conference on Computational Natural Language Learning (CoNLL). Baltimore, MD. PDF

Plank, Barbara; Hovy, Dirk; Søgaard, Anders. 2014. Linguistically debatable or just plain wrong? The 52nd Annual Meeting of the Association for Computational Linguistics (ACL). Baltimore, MD. PDF

Hovy, Dirk; Plank, Barbara; Søgaard, Anders. 2014. Experiments with a crowd-sourced re-annotation of a POS tagging dataset. The 52nd Annual Meeting of the Association for Computational Linguistics (ACL). Baltimore, MD. PDF

Plank, Barbara; Hovy, Dirk; Søgaard, Anders. 2014. Learning part-of-speech taggers with inter-annotator agreement loss. The 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL). Gothenburg, Sweden. Received Best Long Paper Award. PDF

Fromreide, Hege; Søgaard, Anders. 2014. NER in tweets using bagging and a small crowdsourced dataset. The 9th International Conference on Natural Language Processing (PolTAL). Warsaw, Poland. Link

Schluter, Natalie; Elming, Jakob; Søgaard, Anders. 2014. Tree approximations of semantic parsing problems. SemEval 2014. Dublin, Ireland. PDF

Hovy, Dirk; Plank, Barbara; Søgaard, Anders. 2014. When POS datasets do not add up: Combatting sample bias. Language Resources and Evaluation Conference (LREC) 2014. Reykjavik, Iceland. PDF

Pedersen, Bolette; Nimb, Sanni; Olsen, Sussi; Søgaard, Anders; Sørensen, Nicolai. 2014. Semantic annotation of the Danish CLARIN Reference Corpus. 10th Joint ACL-ISO Workshop on Interoperable Semantic Annotation, LREC. Reykjavik, Iceland.

Fromreide, Hege; Søgaard, Anders. 2014. Crowdsourcing and annotating NER for Twitter #drift. Language Resources and Evaluation Conference 2014 (LREC). Reykjavik, Iceland. PDF

2013

Søgaard, Anders. 2013. Semi-supervised learning and domain adaptation for NLP. Morgan & Claypool. Link

Søgaard, Anders; Martinez, Hector; Elming, Jakob; Johannsen, Anders. 2013. Using crowdsourcing to get representations based on regular expressions. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2013. Seattle, WA. PDF

Matthies, Franz; Søgaard, Anders. 2013. With blinkers on: Robust prediction of eye movements across readers. Conference on Empirical Methods in Natural Language Processing (EMNLP) 2013. Seattle, WA. PDF

Søgaard, Anders. 2013. Part-of-speech tagging with antagonistic adversaries. The 51st Annual Meeting of the Association for Computational Linguistics (ACL). Sofia, Bulgaria. PDF

Elming, Jakob; Johannsen, Anders; Klerke, Sigrid; Lapponi, Emanuele; Alonso, Hector Martinez; Søgaard, Anders. 2013. Down-stream effects of tree-to-dependency conversions. North American Chapter of the Association for Computational Linguistics (NAACL). Atlanta, GA. PDF

Søgaard, Anders. 2013. Zipfian corruptions for robust POS tagging. North American Chapter of the Association for Computational Linguistics (NAACL). Atlanta, GA. PDF

Søgaard, Anders. 2013. Estimating effect size across datasets. North American Chapter of the Association for Computational Linguistics (NAACL). Atlanta, GA. PDF

Johannsen, Anders; Søgaard, Anders. 2013. Cross-domain answer ranking using importance sampling. The 6th International Joint Conference on Natural Language Processing (IJCNLP). Nagoya, Japan. PDF

Johannsen, Anders; Søgaard, Anders. 2013. Disambiguating explicit discourse connectives without oracles. The 6th International Joint Conference on Natural Language Processing (IJCNLP). Nagoya, Japan. PDF

Klerke, Sigrid; Søgaard, Anders. 2013. Simple readable sub-sentences. The 51st Annual Meeting of the Association for Computational Linguistics (ACL), Student Research Workshop. Sofia, Bulgaria. PDF

Søgaard, Anders. 2013. An empirical study of differences between conversion schemes and annotation guidelines. International Conference on Dependency Linguistics 2013. Prague, the Czech Republic. PDF

Klerke, Sigrid; Elbro, Carsten; Søgaard, Anders. 2013. Tracking readability in eye movements. 17th European Conference on Eye Movements. Lund, Sweden.

2012

Søgaard, Anders. 2012. Unsupervised dependency parsing without training. Natural Language Engineering 18(1):187-203. Link

Søgaard, Anders; Johannsen, Anders. 2012. Robust learning in random subspaces: equipping NLP for OOV effects. The 24th International Conference on Computational Linguistics (COLING). Mumbai, India. PDF

Søgaard, Anders; Wulff, Julie. 2012. An empirical study of non-lexical extensions to delexicalized transfer. The 24th International Conference on Computational Linguistics (COLING). Mumbai, India. PDF

Søgaard, Anders. 2012. Mining wisdom. Computational Linguistics in Literature, Nothern American Chapter of the Association of Computational Linguistics (NAACL). Montreal, Canada. PDF

Søgaard, Anders. 2012. Two baselines for unsupervised dependency parsing. Workshop on Inducing Linguistic Structure, North American Chapter of the Association of Computational Linguistics (NAACL). Montreal, Canada. PDF

Johannsen, Anders; Martinez, Hector; Klerke, Sigrid; Søgaard, Anders. 2012. EMNLP@CPH: Is frequency all there is to simplicity? SemEval-2012, 1st Joint Conference on Lexical and Computational Semantics. Montreal, Canada. PDF

Nisbeth, Niklas; Søgaard, Anders. 2012. Parser combination under sample bias. SPLeT, Language Resources and Evaluation Conference. Istanbul, Turkey.

Klerke, Sigrid; Søgaard, Anders. 2012. DSim, a Danish parallel corpus for text simplification. The 8th International Conference on Language Resources and Evaluation. Istanbul, Turkey. PDF

Søgaard, Anders; Kristiansen, Søren Lind. 2012. Using hybrid logic for querying dependency treebanks. Linguistic Issues in Language Technology 7(5). Link

Plank, Barbara; Søgaard, Anders. 2012. Parsing the web as covariate shift. First Workshop on Syntactic Analysis of Non-Canonical Language, NAACL 2012. Montreal, Canada. PDF

Plank, Barbara; Søgaard, Anders. 2012. Experiments in newswire-to-law adaptation of graph-based dependency parsers. 8* Convegno Nazionale dell’Associazione Italiana di Scienze della Voce. Rome, Italy. Link

2011

Søgaard, Anders. 2011. A O(|G|n^6) time extension of inversion transduction grammars. Machine Translation 25(4):291-315. Link

Søgaard, Anders; Haulrich, Martin. 2011. Sentence-level instance-weighting for graph-based and transition-based dependency parsing. The 12th International Conference on Parsing Technologies (IWPT). Dublin, Ireland. PDF

Søgaard, Anders. 2011. Semi-supervised condensed nearest neighbor for part-of-speech tagging. The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT). Portland, Oregon. Nominated for Best Short Paper Award. PDF

Søgaard, Anders. 2011. Data point selection for cross-language adaptation of dependency parsers. The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT). Portland, Oregon. PDF

Johannsen, Anders; Martinez, Hector; Rishøj, Christian; Søgaard, Anders. 2011. Frustratingly hard compositionality prediction. Distributional Semantics and Compositionality, the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT). Portland, Oregon. PDF

Søgaard, Anders. 2011. From ranked words to dependency trees: two-stage unsupervised non-projective dependency parsing. TextGraphs-6: Graph-based Methods for Natural Language Processing, the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT). Portland, Oregon. PDF Erratum: The assertion that the algorithm described in the paper does not guarantee projectivity (p. 65) is not true.

Rishøj, Christian; Søgaard, Anders. 2011. Factored translation using unsupervised word clusters. The 6th Workshop on Statistical Machine Translation, Conference on Empirical Methods in Natural Language Processing (EMNLP). Scotland, Edinburgh. PDF

Søgaard, Anders. 2011. Using graphical models for PP attachment. The 18th Nordic Conference on Computational Linguistics (NODALIDA). Riga, Latvia. PDF

Søgaard, Anders. 2011. Learning grammatical functions in a realistic way. The 3rd Conference of the Scandinavian Association for Language and Cognition. Copenhagen, Denmark.

Søgaard, Anders. 2011. Cable television; Fanzines; Functionalist theories; Journalism. In Marcel Danesi (ed.), Encyclopedia of Media and Communication. Toronto: University of Toronto Press.

2010

Søgaard, Anders; Rishøj, Christian. 2010. Semi-supervised dependency parsing using generalized tri-training. The 23rd International Conference on Computational Linguistics (COLING). Beijing, China. PDF

Søgaard, Anders. 2010. Simple semi-supervised training of part-of-speech taggers. The 48th Annual Meeting of the Association for Computational Linguistics (ACL). Uppsala, Sweden. PDF

Søgaard, Anders; Rishøj, Christian. 2010. The effect of semi-supervised learning on parsing long distance dependencies in German and Swedish. The 7th International Conference on Natural Language Processing (IceTAL). Reykjavik, Iceland. Link

Søgaard, Anders; Johannsen, Anders. 2010. Robust semi-supervised and ensemble-based methods in word sense disambiguation. The 7th International Conference on Natural Language Processing (IceTAL). Reykjavik, Iceland. Link

Kristiansen, Søren Lind; Søgaard, Anders. 2010. Querying dependency treebanks in hybrid logic. Hybrid Logic and Applications, The 25th Annual IEEE Symposium on Logic in Computer Science (LICS). Edinburgh, Scotland.

Søgaard, Anders. 2010. Can inversion transduction grammars generate hand alignments? The 14th Annual Conference of the European Association for Machine Translation (EAMT). St. Raphael, France. PDF Erratum: The numbers in Figure 4 are incorrect.

Søgaard, Anders; Haulrich, Martin. 2010. On the derivation perplexity of treebanks. Treebanks and Linguistic Theories 9. Riga, Latvia. PDF

2009

Søgaard, Anders; Lange, Martin. 2009. Polyadic dynamic logics for HPSG parsing. Journal of Logic, Language and Information 18(2): 159-198. Link

Søgaard, Anders; Wu, Dekai. 2009. Empirical lower bounds on translation unit error rate for the full class of inversion transduction grammars. The 11th International Conference on Parsing Technologies (IWPT). Paris, France. PDF

Søgaard, Anders; Kuhn, Jonas. 2009. Using a maximum entropy-based tagger to improve a very fast vine parser. The 11th International Conference on Parsing Technologies (IWPT). Paris, France. PDF

Søgaard, Anders; Kuhn, Jonas. 2009. Empirical lower bounds on aligment error rates in syntax-based machine translation. The 3rd Workshop on Syntax and Structure in Statistical Translation, North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT) 2009. Boulder, Colorado. PDF

Søgaard, Anders. 2009. On the complexity of alignment problems in two synchronous grammar formalisms. The 3rd Workshop on Syntax and Structure in Statistical Translation, North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT) 2009. Boulder, Colorado. PDF

Søgaard, Anders; Østerskov, Stine. 2009. On definitions of consciousness. Journal of Consciousness Studies. Link

Søgaard, Anders. 2009. Compound constructions: a reply to Bundgaard et al. Semiotica: Journal of the International Association for Semiotic Studies 169(1): 163-169. Link

Søgaard, Anders. 2009. Ensemble-based POS tagging of Italian. The 11th Conference of the Italian Association for Artificial Intelligence, EVALITA. Reggio Emilia, Italy. PDF

Søgaard, Anders; Rishøj, Christian. 2009. Vine parsing augmented Italian treebanks. The 11th Conference of the Italian Association for Artificial Intelligence, EVALITA. Reggio Emilia, Italy. PDF

Søgaard, Anders. 2009. A linear time extension of deterministic pushdown automata. The 17th Nordic Conference on Computational Linguistics. Odense, Denmark. PDF

Søgaard, Anders. 2009. Verifying context-sensitive treebanks and heuristic parses in polynomial time. The 17th Nordic Conference on Computational Linguistics (NODALIDA). Odense, Denmark. PDF

Søgaard, Anders; Haugereid, Petter. 2009. Introduction. In Anders Søgaard and Petter Haugereid (eds.), Typed feature structure grammars. Berlin: Peter Lang.

Søgaard, Anders. 2009. From unordered context-free grammar to polysize HPSG without moving. In Anders Søgaard and Petter Haugereid (eds.), Typed feature structure grammars. Berlin: Peter Lang.

2008

Søgaard, Anders. 2008. Range concatenation grammars for translation. The 22nd International Conference on Computational Linguistics (COLING). Manchester, England. PDF

Søgaard, Anders. 2008. On the weak generative capacity of weighted context-free grammars. The 22nd International Conference on Computational Linguistics (COLING). Manchester, England. PDF

Maier, Wolfgang; Søgaard, Anders. 2008. Treebanks and mild context-sensitivity. The 13th Conference on Formal Grammar. Hamburg, Germany. PDF

Søgaard, Anders. 2008. Learning context-sensitive synchronous rules. The 13th Annual Conference on the European Association for Machine Translation (EAMT). Hamburg, Germany. PDF

2007

Søgaard, Anders; Haugereid, Petter. 2007. A tractable typed feature structure grammar for Mainland Scandinavian. Nordic Journal of Linguistics 30(1): 87-128. Link

Søgaard, Anders. 2007. The grammaticalization and disappearance of adpositions in nominal compounds. California Linguistic Notes 17(2): 1-24. PDF

Søgaard, Anders; Lichte, Timm; Maier, Wolfgang. 2007. On the complexity of linguistically motivated extensions of tree-adjoining grammar. Recent Advances in Natural Language Processing 2007. Borovets, Bulgaria. PDF

Søgaard, Anders. 2007. Operations on polyadic structures. Model-theoretic syntax @ 10, the 19th European Summer School on Logic, Language and Information. Dublin, Ireland. PDF

Søgaard, Anders. 2007. Complexity of conceptual integration. The 10th International Cognitive Linguistics Conference. Krakow, Poland.

Søgaard, Anders. 2007. Polynomial charts for totally unordered languages. Proceedings of the 16th Nordic Conference of Computational Linguistics. Tartu, Estonia. PDF

Søgaard, Anders. 2007. Propositional and first order verification of linguistic structures. Proceedings of the 2nd International Workshop on Typed Feature Structure Grammars. Tartu, Estonia. Pp. 17-24.

Søgaard, Anders; Nimb, Sanni. 2007. A typed account of adverbial quantifiers. Proceedings of the 2nd International Workshop on Typed Feature Structure Grammars. Tartu, Estonia. Pp. 53-61.

Søgaard, Anders. 2007. From unordered context-free grammar to polysize HPSG without moving. Proceedings of the 1st International Workshop on Typed Feature Structure Grammars. Aalborg, Denmark. Pp. 17-30.

Søgaard, Anders. 2007. Mathematical properties of natural language and mathematical properties of linguistic theories. The 21st Grammar in Focus. Lund, Sweden.

2006

Søgaard, Anders. 2006. Computational semantics as reasoning about programs. South Asian Language Review 16, Special Issue on Computational Semantics.

Søgaard, Anders. 2006. The semantics of possession in natural language and knowledge representation. Journal of Universal Language 6(2): 85-115.

Søgaard, Anders. 2006. Model generation in a dynamic environment. Takashi Washio, Akito Sakurai, Satoshi Tojo and Makoto Yokoo (eds.), New Frontiers in Artificial Intelligence. Berlin: Springer. Pp. 126-133. Link

Søgaard, Anders. 2006. Unification-based grammars and complexity classes. 8. Konferenz zur Verarbeitung natürlicher Sprache. Konstanz, Germany. Pp. 137-142.

Søgaard, Anders. 2006. Embodied construction grammar as layered modal languages. Proceedings of The Joint Human Language Technology Conference and the North American Chapter of the Association of Computational Linguistics 2006, Third International Workshop on Scalable Natural Language Understanding. New York, New York. PDF

Søgaard, Anders. 2006. Logical investigations on the adequacy of certain feature-based theories of natural language. Proceedings of The Joint Human Language Technology Conference and the North American Chapter of the Association of Computational Linguistics 2006, Doctoral Consortium. New York, New York. PDF

2005

Søgaard, Anders. 2005. Update semantics for HPSG grammars. H. Holmboe (ed.), Nordisk Sprogteknologi 2005. Copenhagen: Museum Tusculanum. Pp. 167-72.

Søgaard, Anders. 2005. Compounding theories and linguistic diversity. Zygmunt Frajzyngier, Adam Hodges and David S. Rood (eds.), Linguistic diversity and language theories. Amsterdam: John Benjamins. Pp. 319-37. Google Books

Søgaard, Anders; Haugereid, Petter. 2005. A brief documentation of a computational HPSG grammar specifying (most of) the common subset of linguistic types for Danish, Norwegian and Swedish. H. Holmboe (ed.), Nordisk Sprogteknologi 2004. Copenhagen: Museum Tusculanum. Pp. 247-56.

Søgaard, Anders. 2005. Where does the meaning of compounds and possessives come from? A contrastive view. The 3rd International Conference in Contrastive Semantics and Pragmatics. Shanghai, China.

Søgaard, Anders. 2005. Computing sense and reference. Computing and Philosophy 2005. Västerås, Sweden.

Søgaard, Anders; Haugereid, Petter. 2005. Functionality in grammar design. The 15th Nordic Conference of Computational Linguistics (NODALIDA). Joensuu, Finland. PDF

Søgaard, Anders. 2005. Model generation in a dynamic environment. Proceedings of Logic and Engineering of Natural Language Semantics 2005. Kitakyushu, Japan.

Søgaard, Anders. 2005. Extending the HPSG Grammar Matrix with richer lexical semantics. Proceedings of The 3rd International Workshop on Generative Approaches to the Lexicon. Geneva, Switzerland.

2004

Søgaard, Anders. 2004. A compound matrix. Proceedings of The 11th International Conference on Head-Driven Phrase Structure Grammar (HPSG). Leuven, Belgium. PDF

Søgaard, Anders. 2004. On appropriateness as a relation between ontologies. International Conference on Formal Ontology in Information Systems. Torino, Italy.

Søgaard, Anders. 2004. K-structure: (a prerequisite for) an interlingua. Papers from the 20th Scandinavian Conference of Linguistics. Helsinki, Finland.

Søgaard, Anders; Haugereid, Petter. 2004. The noun phrase in Mainland Scandinavian. The 3nd Meeting of the Scandinavian Network of Grammar Engineering and Machine Translation. Gothenburg, Sweden.

2003

Søgaard, Anders. 2003. A compound algorithm. Computational Linguistics in the Netherlands 2003. Antwerpen, Belgium.

Søgaard, Anders. 2003. Compounding and the generative lexicon. Sprache, Wissen, Wissenschaft. Munich, Germany.