Trevor Cohn

Tokenizer-Aware Cross-Lingual Adaptation of Decoder-Only LLMs through Embedding Relearning and Swapping EACL 2026 LORAXBENCH: A Multitask, Multilingual Benchmark Suite for 20 Indonesian Languages EMNLP 2025 OpenWHO: A Document-Level Parallel Corpus for Health Translation in Low-Resource Languages EMNLP 2025 TUBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning ACL 2025 Mufu: Multilingual Fused Learning for Low-Resource Translation with LLM ICLR 2025 Planning in the Dark: LLM-Symbolic Planning Pipeline Without Experts AAAI 2025 Tulun: Transparent and Adaptable Low-resource Machine Translation ACL 2025 Improving Language Model Distillation through Hidden State Matching ICLR 2025 Backdoor Attacks on Multilingual Machine Translation NAACL 2024 Simpson’s Paradox and the Accuracy-Fluency Tradeoff in Translation ACL 2024 Revisiting subword tokenization: A case study on affixal negation in large language models NAACL 2024 Pre-training Cross-lingual Open Domain Question Answering with Large-scale Synthetic Supervision EMNLP 2024 Probing Power by Prompting: Harnessing Pre-trained Language Models for Power Connotation Framing EACL 2023 A Survey for Efficient Open Domain Question Answering ACL 2023 Rethinking Round-Trip Translation for Machine Translation Evaluation ACL 2023 Cost-effective Distillation of Large Language Models ACL 2023 Predicting Human Translation Difficulty Using Automatic Word Alignment ACL 2023 Language models are not naysayers: an analysis of language models on negation benchmarks ACL 2023 Seeking Clozure: Robust Hypernym extraction from BERT with Anchored Prompts ACL 2023 IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks ACL 2023 Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP EACL 2023 It’s not only What You Say, It’s also Who It’s Said to: Counterfactual Analysis of Interactive Behavior in the Courtroom AACL 2023 Everybody Needs Good Neighbours: An Unsupervised Locality-based Method for Bias Mitigation ICLR 2023 Super-SCOTUS: A multi-sourced dataset for the Supreme Court of the US EMNLP 2023 Multi-EuP: The Multilingual European Parliament Dataset for Analysis of Bias in Information Retrieval EMNLP 2023 Noisy Self-Training with Synthetic Queries for Dense Retrieval EMNLP 2023 DeltaScore: Fine-Grained Story Evaluation with Perturbations EMNLP 2023 More than Votes? Voting and Language based Partisanship in the US Supreme Court EMNLP 2023 Boot and Switch: Alternating Distillation for Zero-Shot Dense Retrieval EMNLP 2023 It’s not only What You Say, It’s also Who It’s Said to: Counterfactual Analysis of Interactive Behavior in the Courtroom IJCNLP 2023 Mitigating Backdoor Poisoning Attacks through the Lens of Spurious Correlation EMNLP 2023 Don’t Mess with Mister-in-Between: Improved Negative Search for Knowledge Graph Completion EACL 2023 Performance Prediction via Bayesian Matrix Factorisation for Multilingual Natural Language Processing Tasks EACL 2023 WAX: A New Dataset for Word Association eXplanations AACL 2022 Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation AACL 2022 FairLib: A Unified Framework for Assessing and Improving Fairness EMNLP 2022 Unsupervised Cross-Lingual Transfer of Structured Predictors without Source Data NAACL 2022 Systematic Evaluation of Predictive Fairness IJCNLP 2022 WAX: A New Dataset for Word Association eXplanations IJCNLP 2022 Not another Negation Benchmark: The NaN-NLI Test Suite for Sub-clausal Negation IJCNLP 2022 Systematic Evaluation of Predictive Fairness AACL 2022 Incorporating Constituent Syntax for Coreference Resolution AAAI 2022 Does Representational Fairness Imply Empirical Fairness? AACL 2022 LED down the rabbit hole: exploring the potential of global attention for biomedical multi-document summarisation COLING 2022 Foiling Training-Time Attacks on Neural Machine Translation Systems EMNLP 2022 Improving negation detection with negation-focused pre-training NAACL 2022 Towards Fair Dataset Distillation for Text Classification EMNLP 2022 Measuring and Mitigating Name Biases in Neural Machine Translation ACL 2022 Optimising Equal Opportunity Fairness in Model Training NAACL 2022 Balancing out Bias: Achieving Fairness Through Balanced Training EMNLP 2022 Decoupling Adversarial Training for Fair NLP ACL 2021 It Is Not As Good As You Think! Evaluating Simultaneous Machine Translation on Interpretation Data EMNLP 2021 Evaluating Debiasing Techniques for Intersectional Biases EMNLP 2021 Fairness-aware Class Imbalanced Learning EMNLP 2021 Framing Unpacked: A Semi-Supervised Interpretable Multi-View Model of Media Frames NAACL 2021 Incorporating Syntax and Semantics in Coreference Resolution with Heterogeneous Graph Attention Network NAACL 2021 Mitigating Data Poisoning in Text Classification with Differential Privacy EMNLP 2021 Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoning ACL 2021 As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation ACL 2021 PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging ACL 2021 Commonsense Knowledge in Word Associations and ConceptNet EMNLP 2021 Commonsense Knowledge in Word Associations and ConceptNet CONLL 2021 PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging IJCNLP 2021 Learning Coupled Policies for Simultaneous Machine Translation using Imitation Learning EACL 2021 Diverse Adversaries for Mitigating Bias in Training EACL 2021 PPT: Parsimonious Parser Transfer for Unsupervised Cross-Lingual Adaptation EACL 2021 As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation IJCNLP 2021 Putting words into the system’s mouth: A targeted attack on neural machine translation using monolingual data poisoning IJCNLP 2021 Decoupling Adversarial Training for Fair NLP IJCNLP 2021 PTST-UoM at SemEval-2021 Task 10: Parsimonious Transfer for Sequence Tagging SEMEVAL 2021 Decoding As Dynamic Programming For Recurrent Autoregressive Models ICLR 2020 Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics ACL 2020 Improving Chemical Named Entity Recognition in Patents with Contextualized Word Embeddings ACL 2019 Putting Evaluation in Context: Contextual Embeddings Improve Machine Translation Evaluation ACL 2019 Semi-supervised Stochastic Multi-Domain Learning using Variational Inference ACL 2019 Massively Multilingual Transfer for NER ACL 2019 Exploiting Worker Correlation for Label Aggregation in Crowdsourcing ICML 2019 Grounding learning of modifier dynamics: An application to color naming EMNLP 2019 Deep Ordinal Regression for Pledge Specificity Prediction EMNLP 2019 Contextualization of Morphological Inflection NAACL 2019 On the Role of Scene Graphs in Image Captioning EMNLP 2019 Deep Ordinal Regression for Pledge Specificity Prediction IJCNLP 2019 Neural Speech Translation using Lattice Transformations and Graph Networks EMNLP 2019 Grounding learning of modifier dynamics: An application to color naming IJCNLP 2019 Semi-supervised User Geolocation via Graph Convolutional Networks ACL 2018 A Stochastic Decoder for Neural Machine Translation ACL 2018 Graph-to-Sequence Learning using Gated Graph Neural Networks ACL 2018 Hierarchical Structured Model for Fine-to-Coarse Manifesto Text Analysis NAACL 2018 Recurrent Entity Networks with Delayed Memory Update for Targeted Aspect-Based Sentiment Analysis NAACL 2018 What’s in a Domain? Learning Domain-Robust Text Representations using Adversarial Training NAACL 2018 Twitter Geolocation using Knowledge-Based Methods EMNLP 2018 Evaluating the Utility of Hand-crafted Features in Sequence Labelling EMNLP 2018 Iterative Back-Translation for Neural Machine Translation ACL 2018 Narrative Modeling with Memory Chains and Semantic Supervision ACL 2018 Content-based Popularity Prediction of Online Petitions Using a Deep Regression Model ACL 2018 Towards Robust and Privacy-preserving Text Representations ACL 2018 Deep-speare: A joint neural model of poetic language, meter and rhyme ACL 2018 Compressed Nonparametric Language Modelling IJCAI 2017 Capturing Long-range Contextual Dependencies with Memory-enhanced Conditional Random Fields IJCNLP 2017 Topically Driven Neural Language Model ACL 2017 A Neural Model for User Geolocation and Lexical Dialectology ACL 2017 Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary ACL 2017 Multilingual Training of Crosslingual Word Embeddings EACL 2017 Cross-Lingual Word Embeddings for Low-Resource Language Modeling EACL 2017 Robust Training under Linguistic Adversity EACL 2017 Context-Aware Prediction of Derivational Word-forms EACL 2017 Learning Kernels over Strings using Gaussian Processes IJCNLP 2017 Towards Decoding as Continuous Optimisation in Neural Machine Translation EMNLP 2017 Continuous Representation of Location for Geolocation and Lexical Dialectology using Mixture Density Networks EMNLP 2017 Learning how to Active Learn: A Deep Reinforcement Learning Approach EMNLP 2017 Sequence Effects in Crowdsourced Annotations EMNLP 2017 Modelling the Working Week for Multi-Step Forecasting using Gaussian Process Regression IJCAI 2017 End-to-end Network for Twitter Geolocation Prediction and Hashing IJCNLP 2017 Learning Robust Representations of Text EMNLP 2016 Richer Interpolative Smoothing Based on Modified Kneser-Ney Language Modeling EMNLP 2016 Exploring Prediction Uncertainty in Machine Translation Quality Estimation CONLL 2016 Learning when to trust distant supervision: An application to low-resource POS tagging using cross-lingual projection CONLL 2016 Succinct Data Structures for NLP-at-Scale COLING 2016 Learning a Translation Model from Word Lattices INTERSPEECH 2016 pigeo: A Python Geotagging Tool ACL 2016 Hawkes Processes for Continuous Time Sequence Classification: an Application to Rumour Stance Classification in Twitter ACL 2016 Take and Took, Gaggle and Goose, Book and Read: Evaluating the Utility of Vector Differences for Lexical Relation Learning ACL 2016 Incorporating Structural Alignment Biases into an Attentional Neural Translation Model NAACL 2016 An Attentional Model for Speech Translation Without Transcription NAACL 2016 Incorporating Side Information into Recurrent Neural Network Language Models NAACL 2016 Learning a Lexicon and Translation Model from Phoneme Lattices EMNLP 2016 Learning Crosslingual Word Embeddings without Bilingual Corpora EMNLP 2016 Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser IJCNLP 2015 Low Resource Dependency Parsing: Cross-lingual Parameter Sharing in a Neural Network Parser ACL 2015 Classifying Tweet Level Judgements of Rumours in Social Media EMNLP 2015 Compact, Efficient and Unlimited Capacity: Language Modeling with Compressed Suffix Trees EMNLP 2015 A Neural Network Model for Low-Resource Universal Dependency Parsing EMNLP 2015 Modeling Tweet Arrival Times using Log-Gaussian Cox Processes EMNLP 2015 Twitter User Geolocation Using a Unified Text and Network Prediction Model ACL 2015 Point Process Modelling of Rumour Dynamics in Social Media ACL 2015 Cross-lingual Transfer for Unsupervised Dependency Parsing Without Parallel Data CONLL 2015 Non-Linear Text Regression with a Deep Convolutional Neural Network ACL 2015 Twitter User Geolocation Using a Unified Text and Network Prediction Model IJCNLP 2015 Exploiting Text and Network Context for Geolocation of Social Media Users NAACL 2015 Point Process Modelling of Rumour Dynamics in Social Media IJCNLP 2015 Non-Linear Text Regression with a Deep Convolutional Neural Network IJCNLP 2015 Simple extensions and POS Tags for a reparameterised IBM Model 2 ACL 2014 Gaussian Processes for Natural Language Processing ACL 2014 Factored Markov Translation with Robust Modeling CONLL 2014 Predicting and Characterising User Impact on Twitter EACL 2014 What Can We Get From 1000 Tokens? A Case Study of Multilingual POS Tagging For Resource-Poor Languages EMNLP 2014 Joint Emotion Analysis via Multi-task Gaussian Processes EMNLP 2014 A Markov Model of Machine Translation using Non-parametric Bayesian Inference ACL 2013 A user-centric model of voting intention from Social Media ACL 2013 Reducing Annotation Effort for Quality Estimation via Active Learning ACL 2013 Modelling Annotator Bias with Multi-task Gaussian Processes: An Application to Machine Translation Quality Estimation ACL 2013 QuEst - A translation quality estimation framework ACL 2013 An Infinite Hierarchical Bayesian Model of Phrasal Translation ACL 2013 A temporal model of text periodicities using Gaussian Processes EMNLP 2013 Using Senses in HMM Word Alignment NAACL 2012 Evaluating a Morphological Analyser of Inuktitut NAACL 2012 Left-to-Right Tree-to-String Decoding with Prediction EMNLP 2012 Left-to-Right Tree-to-String Decoding with Prediction CONLL 2012 Proceedings of the NAACL-HLT Workshop on the Induction of Linguistic Structure NAACL 2012 The PASCAL Challenge on Grammar Induction NAACL 2012 A Hierarchical Pitman-Yor Process HMM for Unsupervised Part of Speech Induction ACL 2011 Multi-Document Summarization Using A* Search and Discriminative Learning EMNLP 2010 Inducing Tree-Substitution Grammars JMLR 2010 Unsupervised Induction of Tree Substitution Grammars for Dependency Parsing EMNLP 2010 Inducing Synchronous Grammars with Slice Sampling NAACL 2010 Blocked Inference in Bayesian Tree Substitution Grammars ACL 2010 A Note on the Implementation of Hierarchical Dirichlet Processes IJCNLP 2009 A Gibbs Sampler for Phrasal Synchronous Grammar Induction IJCNLP 2009 A Bayesian Model of Syntax-Directed Tree to String Grammar Induction EMNLP 2009 Word Lattices for Multi-Source Translation EACL 2009 Inducing Compact but Accurate Tree-Substitution Grammars NAACL 2009 A Note on the Implementation of Hierarchical Dirichlet Processes ACL 2009 A Gibbs Sampler for Phrasal Synchronous Grammar Induction ACL 2009 Sentence Compression Beyond Word Deletion COLING 2008 Bayesian Synchronous Grammar Induction NIPS 2008 ParaMetric: An Automatic Evaluation Metric for Paraphrasing COLING 2008 A Discriminative Latent Variable Model for Statistical Machine Translation ACL 2008 Large Margin Synchronous Generation and its Application to Sentence Compression CONLL 2007 Large Margin Synchronous Generation and its Application to Sentence Compression EMNLP 2007 Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora ACL 2007 Discriminative Word Alignment with Conditional Random Fields COLING 2006 Discriminative Word Alignment with Conditional Random Fields ACL 2006 Semantic Role Labelling with Tree Conditional Random Fields CONLL 2005 Logarithmic Opinion Pools for Conditional Random Fields ACL 2005 Scaling Conditional Random Fields Using Error-Correcting Codes ACL 2005