Grzegorz Kondrak

Word Surprisal Correlates with Sentential Contradiction in LLMs EACL 2026 UAlberta at SemEval-2025 Task 2: Prompting and Ensembling for Entity-Aware Translation ACL 2025 UAlberta at SemEval-2025 Task 2: Prompting and Ensembling for Entity-Aware Translation SEMEVAL 2025 Semi-Automated Construction of Sense-Annotated Datasets for Practically Any Language COLING 2025 Identifying Emotional and Polar Concepts via Synset Translation NAACL 2024 Paraphrase Identification via Textual Inference NAACL 2024 UAlberta at SemEval-2024 Task 1: A Potpourri of Methods for Quantifying Multilingual Semantic Textual Relatedness and Similarity NAACL 2024 Lexical Substitution as Causal Language Modeling NAACL 2024 Semantically-Prompted Language Models Improve Visual Descriptions NAACL 2024 UAlberta at SemEval-2024 Task 1: A Potpourri of Methods for Quantifying Multilingual Semantic Textual Relatedness and Similarity SEMEVAL 2024 Translation-based Lexicalization Generation and Lexical Gap Detection: Application to Kinship Terms ACL 2024 One Sense per Translation AACL 2023 Grounding the Lexical Substitution Task in Entailment ACL 2023 Taxonomy of Problems in Lexical Semantics ACL 2023 UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation SEMEVAL 2023 Bridging the Gap Between BabelNet and HowNet: Unsupervised Sense Alignment and Sememe Prediction EACL 2023 One Sense per Translation IJCNLP 2023 Don’t Trust ChatGPT when your Question is not in English: A Study of Multilingual Abilities and Types of LLMs EMNLP 2023 UAlberta at SemEval-2023 Task 1: Context Augmentation and Translation for Multilingual Visual Word Sense Disambiguation ACL 2023 WiC = TSV = WSD: On the Equivalence of Three Semantic Tasks NAACL 2022 UAlberta at SemEval 2022 Task 2: Leveraging Glosses and Translations for Multilingual Idiomaticity Detection SEMEVAL 2022 UAlberta at SemEval 2022 Task 2: Leveraging Glosses and Translations for Multilingual Idiomaticity Detection NAACL 2022 UAlberta at LSCDiscovery: Lexical Semantic Change Detection via Word Sense Disambiguation ACL 2022 Improving HowNet-Based Chinese Word Sense Disambiguation with Translations EMNLP 2022 UAlberta at SemEval-2021 Task 2: Determining Sense Synonymy via Translations IJCNLP 2021 UAlberta at SemEval-2021 Task 2: Determining Sense Synonymy via Translations SEMEVAL 2021 Homonymy and Polysemy Detection with Multilingual Information EACL 2021 On Universal Colexifications EACL 2021 UAlberta at SemEval-2021 Task 2: Determining Sense Synonymy via Translations ACL 2021 One Homonym per Translation AAAI 2020 Low-Resource G2P and P2G Conversion with Synthetic Training Data ACL 2020 UAlberta at SemEval-2020 Task 2: Using Translations to Predict Cross-Lingual Entailment COLING 2020 Improving Word Sense Disambiguation with Translations EMNLP 2020 UAlberta at SemEval-2020 Task 2: Using Translations to Predict Cross-Lingual Entailment SEMEVAL 2020 Cognate Projection for Low-Resource Inflection Generation ACL 2019 Joint Approach to Deromanization of Code-mixed Texts NAACL 2019 Comparison of Assorted Models for Transliteration ACL 2018 String Transduction with Target Language Models and Insertion Handling EMNLP 2018 Combining Neural and Non-Neural Methods for Low-Resource Morphological Reinflection CONLL 2018 Bootstrapping Unsupervised Bilingual Lexicon Induction EACL 2017 If you can’t beat them, join them: the University of Alberta system description CONLL 2017 Morphological Analysis without Expert Annotation EACL 2017 Identifying Cognate Sets Across Dictionaries of Related Languages EMNLP 2017 Leveraging Inflection Tables for Stemming and Lemmatization. ACL 2016 Integrating Morphological Desegmentation into Phrase-based Decoding NAACL 2016 A Lexicalized Tree Kernel for Open Information Extraction ACL 2015 A Lexicalized Tree Kernel for Open Information Extraction IJCNLP 2015 Joint Generation of Transliterations from Multiple Representations NAACL 2015 Inflection Generation as Discriminative String Transduction NAACL 2015 English orthography is not “close to optimal” NAACL 2015 Solving Substitution Ciphers with Combined Language Models COLING 2014 Does the Phonology of L1 Show Up in L2 Texts? ACL 2014 Lattice Desegmentation for Statistical Machine Translation ACL 2014 Reversing Morphological Tokenization in English-to-Arabic SMT NAACL 2013 Identification of Speakers in Novels ACL 2013 Automatic Generation of English Respellings NAACL 2013 Leveraging supplemental representations for sequential transduction NAACL 2012 How do you pronounce your name? Improving G2P with transliterations ACL 2011 The application of chordal graphs to inferring phylogenetic trees of languages IJCNLP 2011 Clustering Semantically Equivalent Words into Cognate Sets in Multilingual Lists IJCNLP 2011 Predicting the Semantic Compositionality of Prefix Verbs EMNLP 2010 Language identification of names with SVMs NAACL 2010 Integrating Joint n-gram Features into a Discriminative Training Framework NAACL 2010 Letter-Phoneme Alignment: An Exploration ACL 2010 On the Syllabification of Phonemes NAACL 2009 Reducing the Annotation Effort for Letter-to-Phoneme Conversion IJCNLP 2009 A Ranking Approach to Stress Prediction for Letter-to-Phoneme Conversion IJCNLP 2009 Reducing the Annotation Effort for Letter-to-Phoneme Conversion ACL 2009 A Ranking Approach to Stress Prediction for Letter-to-Phoneme Conversion ACL 2009 Multiple Word Alignment with Profile Hidden Markov Models NAACL 2009 Joint Processing and Discriminative Training for Letter-to-Phoneme Conversion ACL 2008 Automatic Syllabification with Structured SVMs for Letter-to-Phoneme Conversion ACL 2008 Bootstrapping a Stochastic Transducer for Arabic-English Transliteration Extraction ACL 2007 Substring-Based Transliteration ACL 2007 Alignment-Based Discriminative String Similarity ACL 2007 A Fast Method for Parallel Document Identification NAACL 2007 Applying Many-to-Many Alignments and Hidden Markov Models to Letter-to-Phoneme Conversion NAACL 2007 Learning a Spelling Error Model from Search Query Logs EMNLP 2005 Computing Word Similarity and Identifying Cognates with Pair Hidden Markov Models CONLL 2005 Identification of Confusable Drug Names: A New Approach and Evaluation Methodology COLING 2004 Cognates Can Improve Statistical Translation Models NAACL 2003 Determining Recurrent Sound Correspondences by Inducing Translation Models COLING 2002 Identifying Cognates by Phonetic and Semantic Similarity NAACL 2001 A New Algorithm for the Alignment of Phonetic Sequences NAACL 2000