Anders Søgaard

Realist and Pluralist Conceptions of Intelligence and Their Implications on AI Research AAAI 2026 LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation AAAI 2026 NLP for Social Good: A Survey and Outlook of Challenges, Opportunities and Responsible Deployment EACL 2026 LLM Beliefs Are in Their Heads ACL 2026 Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users ACL 2025 Do Language Models Have Semantics? On the Five Standard Positions ACL 2025 Understanding Subword Compositionality of Large Language Models EMNLP 2025 Ethical Concern Identification in NLP: A Corpus of ACL Anthology Ethics Statements NAACL 2025 What if Othello-Playing Language Models Could See? EMNLP 2025 Lost in Embeddings: Information Loss in Vision–Language Models EMNLP 2025 SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval SEMEVAL 2025 Debiasing Multilingual LLMs in Cross-lingual Latent Space EMNLP 2025 SemEval-2025 Task 7: Multilingual and Crosslingual Fact-Checked Claim Retrieval ACL 2025 Trick or Neat: Adversarial Ambiguity and Language Model Evaluation ACL 2025 How Do Multilingual Language Models Remember Facts? ACL 2025 FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture EMNLP 2024 Defining Knowledge: Bridging Epistemology and Large Language Models EMNLP 2024 Unlocking Markets: A Multilingual Benchmark to Cross-Market Question Answering EMNLP 2024 On Mitigating Performance Disparities in Multilingual Speech Recognition EMNLP 2024 Concept Space Alignment in Multilingual LLMs EMNLP 2024 Vision-Language Models under Cultural and Inclusive Considerations ACL 2024 The Impact of Differential Privacy on Group Disparity Mitigation NAACL 2024 Group Fairness in Multilingual Speech Recognition Models NAACL 2024 MuLan: A Study of Fact Mutability in Language Models NAACL 2024 Evaluating Webcam-based Gaze Data as an Alternative for Human Rationale Annotations COLING 2024 What does the Failure to Reason with “Respectively” in Zero/Few-Shot Settings Tell Us about Language Models? ACL 2023 Copyright Violations and Large Language Models EMNLP 2023 Being Right for Whose Right Reasons? ACL 2023 Grammatical Error Correction through Round-Trip Machine Translation EACL 2023 LeXFiles and LegalLAMA: Facilitating English Multinational Legal Language Model Development ACL 2023 A Two-Sided Discussion of Preregistration of NLP Research EACL 2023 Mapping Brains with Language Models: A Survey ACL 2023 Differential Privacy, Linguistic Fairness, and Training Data Influence: Impossibility and Possibility Theorems for Multilingual Language Models ICML 2023 Are Pretrained Multilingual Models Equally Fair across Languages? COLING 2022 Should We Ban English NLP for a Year? EMNLP 2022 Are Multilingual Sentiment Models Equally Right for the Right Reasons? EMNLP 2022 Do Transformer Models Show Similar Attention Patterns to Task-Specific Human Gaze? ACL 2022 FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing ACL 2022 Word Order Does Matter and Shuffled Language Models Know It ACL 2022 Zero-Shot Dependency Parsing with Worst-Case Aware Automated Curriculum Learning ACL 2022 Challenges and Strategies in Cross-Cultural NLP ACL 2022 Square One Bias in NLP: Towards a Multi-Dimensional Exploration of the Research Manifold ACL 2022 QLEVR: A Diagnostic Dataset for Quantificational Language and Elementary Visual Reasoning NAACL 2022 Generalized Quantifiers as a Source of Error in Multilingual NLU Benchmarks NAACL 2022 How Conservative are Language Models? Adapting to the Introduction of Gender-Neutral Pronouns NAACL 2022 Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting ACL 2022 Factual Consistency of Multilingual Pretrained Language Models ACL 2022 Ancestor-to-Creole Transfer is Not a Walk in the Park ACL 2022 Attention Can Reflect Syntactic Structure (If You Let It) EACL 2021 Multilingual Negation Scope Resolution for Clinical Text EACL 2021 Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color CONLL 2021 A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs CONLL 2021 Analogy Training Multilingual Encoders AAAI 2021 Moses and the Character-Based Random Babbling Baseline: CoAStaL at AmericasNLP 2021 Shared Task NAACL 2021 Do Language Models Know the Way to Rome? EMNLP 2021 Locke’s Holiday: Belief Bias in Machine Reading EMNLP 2021 Dynamic Forecasting of Conversation Derailment EMNLP 2021 Sociolectal Analysis of Pretrained Language Models EMNLP 2021 The Effect of Round-Trip Translation on Fairness in Sentiment Analysis EMNLP 2021 John praised Mary because _he_? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs IJCNLP 2021 Minimax and Neyman–Pearson Meta-Learning for Outlier Languages IJCNLP 2021 How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task IJCNLP 2021 On the Interaction of Belief Bias and Explanations IJCNLP 2021 Itihasa: A large-scale corpus for Sanskrit to English translation IJCNLP 2021 Spurious Correlations in Cross-Topic Argument Mining IJCNLP 2021 Guideline Bias in Wizard-of-Oz Dialogues IJCNLP 2021 The Impact of Positional Encodings on Multilingual Compression EMNLP 2021 Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards AAAI 2021 Replicating and Extending “Because Their Treebanks Leak”: Graph Isomorphism, Covariants, and Parser Performance IJCNLP 2021 Common Sense Bias in Semantic Role Labeling EMNLP 2021 Evaluation of Summarization Systems across Gender, Age, and Race EMNLP 2021 Clustering Monolingual Vocabularies to Improve Cross-Lingual Generalization EMNLP 2021 Resources and Evaluations for Danish Entity Resolution EMNLP 2021 A Multilingual Benchmark for Probing Negation-Awareness with Minimal Pairs EMNLP 2021 Can Language Models Encode Perceptual Structure Without Grounding? A Case Study in Color EMNLP 2021 On Language Models for Creoles EMNLP 2021 Is the Lottery Fair? Evaluating Winning Tickets Across Demographics IJCNLP 2021 Replicating and Extending “Because Their Treebanks Leak”: Graph Isomorphism, Covariants, and Parser Performance ACL 2021 Minimax and Neyman–Pearson Meta-Learning for Outlier Languages ACL 2021 On the Interaction of Belief Bias and Explanations ACL 2021 Is the Lottery Fair? Evaluating Winning Tickets Across Demographics ACL 2021 John praised Mary because _he_? Implicit Causality Bias and Its Interaction with Explicit Cues in LMs ACL 2021 Guideline Bias in Wizard-of-Oz Dialogues ACL 2021 Spurious Correlations in Cross-Topic Argument Mining ACL 2021 Itihasa: A large-scale corpus for Sanskrit to English translation ACL 2021 How far can we get with one GPU in 100 hours? CoAStaL at MultiIndicMT Shared Task ACL 2021 On Language Models for Creoles CONLL 2021 Ellipsis Resolution as Question Answering: An Evaluation EACL 2021 We Need To Talk About Random Splits EACL 2021 Error Analysis and the Role of Morphology EACL 2021 Some Languages Seem Easier to Parse Because Their Treebanks Leak EMNLP 2020 Do End-to-End Speech Recognition Models Care About Context? INTERSPEECH 2020 What Do You Mean ‘Why?’: Resolving Sluices in Conversations AAAI 2020 The Sensitivity of Language Models and Humans to Winograd Schema Perturbations ACL 2020 Weakly Supervised POS Taggers Perform Poorly on Truly Low-Resource Languages AAAI 2020 Parsing as Pretraining AAAI 2020 Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias EMNLP 2020 Are All Good Word Vector Spaces Isomorphic? EMNLP 2020 Grammatical Error Correction in Low Error Density Domains: A New Benchmark and Analyses EMNLP 2020 Neural Speed Reading Audited EMNLP 2020 A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages IJCNLP 2019 Issue Framing in Online Discussion Fora NAACL 2019 A systematic comparison of methods for low-resource dependency parsing on genuinely low-resource languages EMNLP 2019 Rewarding Coreference Resolvers for Being Consistent with World Knowledge EMNLP 2019 Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary Induction EMNLP 2019 Higher-order Comparisons of Sentence Encoder Representations EMNLP 2019 Adversarial Removal of Demographic Attributes Revisited EMNLP 2019 Few-Shot and Zero-Shot Learning for Historical Text Normalization EMNLP 2019 X-WikiRE: A Large, Multilingual Resource for Relation Extraction as Machine Comprehension EMNLP 2019 Rewarding Coreference Resolvers for Being Consistent with World Knowledge IJCNLP 2019 Lost in Evaluation: Misleading Benchmarks for Bilingual Dictionary Induction IJCNLP 2019 Higher-order Comparisons of Sentence Encoder Representations IJCNLP 2019 Adversarial Removal of Demographic Attributes Revisited IJCNLP 2019 Better, Faster, Stronger Sequence Tagging Constituent Parsers NAACL 2019 A Simple and Robust Approach to Detecting Subject-Verb Agreement Errors NAACL 2019 Comparing Unsupervised Word Translation Methods Step by Step NIPS 2019 CoAStaL at SemEval-2019 Task 3: Affect Classification in Dialogue using Attentive BiLSTMs SEMEVAL 2019 Noisy Channel for Low Resource Grammatical Error Correction ACL 2019 Unsupervised Cross-Lingual Representation Learning ACL 2019 Multi-Task Semantic Dependency Parsing with Policy Gradient for Learning Easy-First Strategies ACL 2019 Historical Text Normalization with Delayed Rewards ACL 2019 Predicting Concrete and Abstract Entities in Modern Poetry AAAI 2019 Latent Multi-Task Architecture Learning AAAI 2019 Jointly Learning to Label Sentences and Tokens AAAI 2019 Sluice Resolution without Hand-Crafted Features over Brittle Syntax Trees NAACL 2018 Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens NAACL 2018 Multi-Task Learning of Pairwise Sequence Classification Tasks over Disparate Label Spaces NAACL 2018 Character-level Supervision for Low-resource POS Tagging ACL 2018 Generalizing Procrustes Analysis for Better Bilingual Dictionary Induction CONLL 2018 Limitations of Cross-Lingual Learning from Image Search ACL 2018 Unsupervised Induction of Linguistic Categories with Records of Reading, Speaking, and Writing NAACL 2018 A Discriminative Latent-Variable Model for Bilingual Lexicon Induction EMNLP 2018 Why is unsupervised alignment of English embeddings from different algorithms so hard? EMNLP 2018 A strong baseline for question relevancy ranking EMNLP 2018 Parameter sharing between dependency parsers for related languages EMNLP 2018 When does deep multi-task learning work for loosely related document classification tasks? EMNLP 2018 Nightmare at test time: How punctuation prevents parsers from generalizing EMNLP 2018 Linguistic representations in multi-task neural networks for ellipsis resolution EMNLP 2018 Sentiment analysis under temporal shift EMNLP 2018 Lexi: A tool for adaptive, personalized text simplification COLING 2018 Sequence Classification with Human Attention CONLL 2018 On the Limitations of Unsupervised Bilingual Dictionary Induction ACL 2018 Multi-task learning for historical text normalization: Size matters ACL 2018 Cross-lingual RST Discourse Parsing EACL 2017 Cross-Lingual Dependency Parsing with Late Decoding for Truly Low-Resource Languages EACL 2017 Using millions of emoji occurrences to learn any-domain representations for detecting sentiment, emotion and sarcasm EMNLP 2017 Does syntax help discourse segmentation? Not so much EMNLP 2017 Cross-Lingual Word Representations: Induction and Evaluation EMNLP 2017 Multi-Task Learning of Keyphrase Boundary Classification ACL 2017 Cross-lingual and cross-domain discourse segmentation of entire documents ACL 2017 Learning attention for historical text normalization by learning to pronounce ACL 2017 Cross-lingual tagger evaluation without test data EACL 2017 Identifying beneficial task relations for multi-task learning in deep neural networks EACL 2017 A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments EACL 2017 Parsing Universal Dependencies without training EACL 2017 Joint part-of-speech and dependency projection from multiple sources ACL 2016 Weakly Supervised Part-of-speech Tagging Using Eye-tracking Data ACL 2016 Improving historical spelling normalization with bi-directional LSTMs and multi-task learning COLING 2016 Cross-lingual Transfer of Correlations between Parts of Speech and Gaze Features COLING 2016 Learning a POS tagger for AAVE-like language NAACL 2016 Improving sentence compression by learning to predict gaze NAACL 2016 Multi-view and multi-task training of RST discourse parsers COLING 2016 Extracting token-level signals of syntactic processing from fMRI - with an application to PoS induction ACL 2016 Deep multi-task learning with low level tasks supervised at lower layers ACL 2016 Text Simplification as Tree Labeling ACL 2016 Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss ACL 2016 Learning to parse with IAA-weighted loss NAACL 2015 Inverted indexing for cross-lingual NLP ACL 2015 If all you have is a bit of the Bible: Learning POS taggers for truly low-resource languages ACL 2015 Tagging Performance Correlates with Author Age ACL 2015 Unsupervised extractive summarization via coverage maximization with syntactic and semantic concepts ACL 2015 Cross-lingual syntactic variation over age and gender CONLL 2015 Do dependency parsing metrics correlate with human judgments? CONLL 2015 Reading behavior predicts syntactic categories CONLL 2015 Any-language frame-semantic parsing EMNLP 2015 Inverted indexing for cross-lingual NLP IJCNLP 2015 If all you have is a bit of the Bible: Learning POS taggers for truly low-resource languages IJCNLP 2015 Tagging Performance Correlates with Author Age IJCNLP 2015 Unsupervised extractive summarization via coverage maximization with syntactic and semantic concepts IJCNLP 2015 Mining for unambiguous instances to adapt part-of-speech taggers to new domains NAACL 2015 Simple task-specific bilingual word embeddings NAACL 2015 Importance weighting and unsupervised domain adaptation of POS taggers: a negative result EMNLP 2014 Linguistically debatable or just plain wrong? ACL 2014 Adapting taggers to Twitter with not-so-distant supervision COLING 2014 Learning part-of-speech taggers with inter-annotator agreement loss EACL 2014 What’s in a p-value in NLP? CONLL 2014 Selection Bias, Label Bias, and Bias in Ground Truth COLING 2014 Experiments with crowdsourced re-annotation of a POS tagging data set ACL 2014 Copenhagen-Malmö: Tree Approximations of Semantic Parsing Problems SEMEVAL 2014 Down-stream effects of tree-to-dependency conversions NAACL 2013 Disambiguating Explicit Discourse Connectives without Oracles IJCNLP 2013 Cross-Domain Answer Ranking using Importance Sampling IJCNLP 2013 Using Crowdsourcing to get Representations based on Regular Expressions EMNLP 2013 With Blinkers on: Robust Prediction of Eye Movements across Readers EMNLP 2013 Simple, readable sub-sentences ACL 2013 Part-of-speech tagging with antagonistic adversaries ACL 2013 Estimating effect size across datasets NAACL 2013 Zipfian corruptions for robust POS tagging NAACL 2013 Mining wisdom NAACL 2012 Robust Learning in Random Subspaces: Equipping NLP for OOV Effects COLING 2012 An Empirical Etudy of Non-Lexical Extensions to Delexicalized Transfer COLING 2012 Two baselines for unsupervised dependency parsing NAACL 2012 EMNLP@CPH: Is frequency all there is to simplicity? SEMEVAL 2012 Semi-supervised condensed nearest neighbor for part-of-speech tagging ACL 2011 Data point selection for cross-language adaptation of dependency parsers ACL 2011 Simple Semi-Supervised Training of Part-Of-Speech Taggers ACL 2010 Semi-supervised dependency parsing using generalized tri-training COLING 2010 Range Concatenation Grammars for Translation COLING 2008 On the Weak Generative Capacity of Weighted Context-free Grammars COLING 2008 Logical investigations on the adequacy of certain feature-based theories of natural language NAACL 2006