Lexical Acquisition Across Languages

Publications

Conference proceedings (40)

Bilingual Lexicon Induction by Learning to Combine Word-Level and Character-Level Representations

Author(s): Geert Heyman, Ivan Vulić, and Marie-Francine Moens
Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), 2017, Page(s) 1085-1095

Evaluation by Association: A Systematic Study of Quantitative Word Association Evaluation

Author(s): Ivan Vulić, Douwe Kiela, and Anna Korhonen
Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), Issue Volume 1, Long Papers, 2017, Page(s) 163-175

Cross-Lingual Syntactically Informed Distributed Word Representations

Author(s): Ivan Vulić
Published in: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017), 2017, Page(s) 408-414

Decoding Sentiment from Distributed Representations of Sentences

Author(s): Edoardo Maria Ponti, Ivan Vulić, Anna Korhonen
Published in: Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017), 2017, Page(s) 22-32
DOI: 10.18653/v1/S17-1003

Morph-fitting: Fine-Tuning Word Vector Spaces with Simple Language-Specific Rules

Author(s): Ivan Vulić, Nikola Mrkšić, Roi Reichart, Diarmuid Ó Séaghdha, Steve Young, Anna Korhonen
Published in: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2017, Page(s) 56-68
DOI: 10.18653/v1/P17-1006

Automatic Selection of Context Configurations for Improved Class-Specific Word Representations

Author(s): Ivan Vulić, Roy Schwartz, Ari Rappoport, Roi Reichart, Anna Korhonen
Published in: Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017), 2017, Page(s) 112-122
DOI: 10.18653/v1/K17-1013

Specialising Word Vectors for Lexical Entailment

Author(s): Ivan Vulić and Nikola Mrkšić
Published in: Proceedings of the 16th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018), Issue long paper, 2018

Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources

Author(s): Ivan Vulić, Goran Glavaš, Nikola Mrkšić, and Anna Korhonen
Published in: Proceedings of the 16th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018), Issue long paper, 2018

Cross-Lingual Induction and Transfer of Verb Classes Based on Word Vector Space Specialisation

Author(s): Ivan Vulić, Nikola Mrkšić, and Anna Korhonen
Published in: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2017), 2017, Page(s) 2536-2548

Event-Related Features in Feedforward Neural Networks Contribute to Identifying Implicit Causal Relations in Discourse

Author(s): Ponti, Edoardo Maria and Anna Korhonen
Published in: Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-level Semantics, 2017, Page(s) 25-30

Acquiring Verb Classes through Bottom-Up Semantic Verb Clustering

Author(s): Olga Majewska, Diana McCarthy, Ivan Vulić, and Anna Korhonen
Published in: Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC 2018), 2018, Page(s) pp. 952-958

Discriminating between Lexico-Semantic Relations with the Specialization Tensor Model

Author(s): Goran Glavaš and Ivan Vulić
Published in: Proceedings of the 16th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT 2018), 2018, Page(s) pp. 181-187

Specialising Word Vectors for Lexical Entailment

Author(s): Vulić, Ivan; Mrkšić, Nikola
Published in: Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Issue Volume 1 (Long Papers), 2018, Page(s) 1134 -1145

Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only

Author(s): Robert Litschko, Goran Glavaš, Simone Paolo Ponzetto, Ivan Vulić
Published in: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval - SIGIR '18, 2018, Page(s) 1253-1256
DOI: 10.1145/3209978.3210157

Injecting Lexical Contrast into Word Vectors by Guiding Vector Space Specialisation

Author(s): Ivan Vulić and Anna Korhonen
Published in: Proceedings of The Third Workshop on Representation Learning for NLP, 2018, Page(s) 137-143

Bridging Languages through Images with Deep Partial Canonical Correlation Analysis

Author(s): Guy Rotman, Ivan Vulić, and Roi Reichart
Published in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Issue long paper, 2018, Page(s) pp. 910-921

Scoring Lexical Entailment with a Supervised Directional Similarity Network

Author(s): Marek Rei, Daniela Gerz, and Ivan Vulić
Published in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Issue (Volume 2: Short Papers), 2018, Page(s) 638-643

Fully Statistical Neural Belief Tracking

Author(s): Nikola Mrkšić and Ivan Vulić
Published in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Issue short paper, 2018, Page(s) pp. 108-113

Explicit Retrofitting of Distributional Word Vectors

Author(s): Goran Glavaš and Ivan Vulić
Published in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Issue Volume 1: Long Papers, 2018, Page(s) pp. 34-45

On the Limitations of Unsupervised Bilingual Dictionary Induction

Author(s): Anders Søgaard, Sebastian Ruder, Ivan Vulić
Published in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, Issue (Volume 1: Long Papers), 2018, Page(s) pp. 778-788
DOI: 10.17863/cam.32410

Isomorphic Transfer of Syntactic Structures in Cross-Lingual Natural Language Processing

Author(s): Edoardo Maria Ponti, Roi Reichart, Anna Korhonen, and Ivan Vulić
Published in: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018), Issue long paper, 2018, Page(s) pp. 1531-1542

"Is ""Universal Syntax"" Universally Useful for Learning Distributed Word Representations? "

Author(s): Ivan Vulic and Anna Korhonen
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Issue Volume 2: Short Papers, 2016, Page(s) 518-524

Multi-Modal Representations for Improved Bilingual Lexicon Learning

Author(s): Ivan Vulić, Douwe Kiela, Stephen Clark, and Marie-Francine Moens
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Issue Volume 2: Short Papers, 2016, Page(s) 188-194

On the Role of Seed Lexicons in Learning Bilingual Word Embeddings

Author(s): Ivan Vulic and Anna Korhonen
Published in: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Issue Volume 1: Long Papers, 2016, Page(s) 247-257
DOI: 10.17863/CAM.9717

SimVerb-3500: A Large-Scale Evaluation Set of Verb Similarity

Author(s): Daniela Gerz, Ivan Vulić, Felix Hill, Roi Reichart, and Anna Korhonen
Published in: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016, Page(s) 2173-2182
DOI: 10.18653/v1/D16-1235

Survey on the Use of Typological Information in Natural Language Processing

Author(s): Helen O'Horan, Yevgeni Berzak, Ivan Vulić, Roi Reichart and Anna Korhonen
Published in: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, 2016, Page(s) 1297-1308

Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization

Author(s): Ponti, Edoardo Maria; Vulić, Ivan; Glavaš, Goran; Mrkšić, Nikola; Korhonen, Anna
Published in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Issue 12, 2018, Page(s) 282--293
DOI: 10.18653/v1/D18-1026

Specializing Distributional Vectors of All Words for Lexical Entailment

Author(s): Aishwarya Kamath, Jonas Pfeiffer, Edoardo Maria Ponti, Goran Glavaš, Ivan Vulić
Published in: Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), 2019, Page(s) 72-83
DOI: 10.18653/v1/w19-4310

Evaluating Resource-Lean Cross-Lingual Embedding Models in Unsupervised Retrieval

Author(s): Robert Litschko, Goran Glavaš, Ivan Vulic, Laura Dietz
Published in: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR'19, 2019, Page(s) 1109-1112
DOI: 10.1145/3331184.3331324

On the Importance of Subword Information for Morphological Tasks in Truly Low-Resource Languages

Author(s): Yi Zhu, Benjamin Heinzerling, Ivan Vulić, Michael Strube, Roi Reichart, Anna Korhonen
Published in: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), 2019, Page(s) 216-226
DOI: 10.18653/v1/k19-1021

Investigating Cross-Lingual Alignment Methods for Contextualized Embeddings with Token-Level Evaluation

Author(s): Qianchu Liu, Diana McCarthy, Ivan Vulić, Anna Korhonen
Published in: Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), 2019, Page(s) 33-43
DOI: 10.18653/v1/k19-1004

Hello, It’s GPT-2 - How Can I Help You? Towards the Use of Pretrained Language Models for Task-Oriented Dialogue Systems

Author(s): Paweł Budzianowski, Ivan Vulić
Published in: Proceedings of the 3rd Workshop on Neural Generation and Translation, 2019, Page(s) 15-22
DOI: 10.18653/v1/d19-5602

Cross-lingual Semantic Specialization via Lexical Relation Induction

Author(s): Edoardo Maria Ponti, Ivan Vulić, Goran Glavaš, Roi Reichart, Anna Korhonen
Published in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, Page(s) 2206-2217
DOI: 10.18653/v1/d19-1226

Do We Really Need Fully Unsupervised Cross-Lingual Embeddings?

Author(s): Ivan Vulić, Goran Glavaš, Roi Reichart, and Anna Korhonen
Published in: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP 2019), 2019, Page(s) 4406-4417
DOI: 10.18653/v1/d19-1449

Towards Zero-shot Language Modeling

Author(s): Edoardo Maria Ponti, Ivan Vulić, Ryan Cotterell, Roi Reichart, Anna Korhonen
Published in: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019, Page(s) 2900-2910
DOI: 10.18653/v1/d19-1288

A General Framework for Implicit and Explicit Debiasing of Distributional Word Vector Spaces

Author(s): Anne Lauscher, Goran Glavaš, Simone Paolo Ponzetto, and Ivan Vulić
Published in: Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020), Issue long paper, to appear, 2020

Enhancing biomedical word embeddings by retrofitting to verb clusters

Author(s): Billy Chiu, Simon Baker, Martha Palmer, Anna Korhonen
Published in: Proceedings of the 18th BioNLP Workshop and Shared Task, 2019, Page(s) 125-134
DOI: 10.18653/v1/w19-5014

Show Some Love to Your n-grams: A Bit of Progress and Stronger n-gram Language Modeling Baselines

Author(s): Ehsan Shareghi, Daniela Gerz, Ivan Vulić, Anna Korhonen
Published in: Proceedings of the 2019 Conference of the North, 2019, Page(s) 4113-4118
DOI: 10.18653/v1/n19-1417

On the Relation between Linguistic Typology and (Limitations of) Multilingual Language Modeling

Author(s): Daniela Gerz, Ivan Vulić, Edoardo Maria Ponti, Roi Reichart, Anna Korhonen
Published in: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018, Page(s) 316-327
DOI: 10.18653/v1/d18-1029

Bayesian learning for neural dependency parsing

Author(s): Ehsan Shareghi, Yingzhen Li, Yi Zhu, Roi Reichart, Anna Korhonen
Published in: Proceedings of the 2019 Conference of the North, 2019, Page(s) 3509-3519
DOI: 10.18653/v1/n19-1354

Peer reviewed articles (8)

Investigating the cross-lingual translatability of VerbNet-style classification

Author(s): Olga Majewska, Ivan Vulić, Diana McCarthy, Yan Huang, Akira Murakami, Veronika Laippala, Anna Korhonen
Published in: Language Resources and Evaluation, 2017, ISSN 1574-020X
DOI: 10.1007/s10579-017-9403-x

HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment

Author(s): Ivan Vulić, Daniela Gerz, Douwe Kiela, Felix Hill, Anna Korhonen
Published in: Computational Linguistics, Issue 43/4, 2017, Page(s) 781-835, ISSN 0891-2017
DOI: 10.1162/COLI_a_00301

Bio-SimVerb and Bio-SimLex: wide-coverage evaluation sets of word similarity in biomedicine

Author(s): Billy Chiu, Sampo Pyysalo, Ivan Vulić, Anna Korhonen
Published in: BMC Bioinformatics, Issue 19/1, 2018, ISSN 1471-2105
DOI: 10.1186/s12859-018-2039-z

Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints

Author(s): Nikola Mrkšić, Ivan Vulić, Diarmuid Ó Séaghdha, Roi Reichart, Ira Leviant, Milica Gašić, Anna Korhonen, and Steve Young
Published in: Transactions of the Association for Computational Linguistics, presented at EMNLP 2017, Issue vol. 5, 2017, Page(s) 309-324, ISSN 2307-387X

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Author(s): Ivan Vulić and Marie-Francine Moens
Published in: Journal of Artificial Intelligence Research, Issue Volume 55, 2016, Page(s) 953-994, ISSN 1076-9757
DOI: 10.1613/jair.4986

Language Modeling for Morphologically Rich Languages: Character-Aware Modeling for Word-Level Prediction

Author(s): Daniela Gerz, Ivan Vulić, Edoardo Ponti, Jason Naradowsky, Roi Reichart, Anna Korhonen
Published in: Transactions of the Association for Computational Linguistics, Issue 6, 2018, Page(s) 451-465, ISSN 2307-387X
DOI: 10.1162/tacl_a_00032

Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing

Author(s): Edoardo Maria Ponti, Helen O’Horan, Yevgeni Berzak, Ivan Vulić, Roi Reichart, Thierry Poibeau, Ekaterina Shutova, Anna Korhonen
Published in: Computational Linguistics, Issue 45/3, 2019, Page(s) 559-601, ISSN 0891-2017
DOI: 10.1162/coli_a_00357

A neural classification method for supporting the creation of BioVerbNet

Author(s): Billy Chiu, Olga Majewska, Sampo Pyysalo, Laura Wey, Ulla Stenius, Anna Korhonen, Martha Palmer
Published in: Journal of Biomedical Semantics, Issue 10/1, 2019, ISSN 2041-1480
DOI: 10.1186/s13326-018-0193-x

Book chapters (1)

Zero-Shot Language Transfer for Cross-Lingual Sentence Retrieval Using Bidirectional Attention Model

Author(s): Goran Glavaš, Ivan Vulić
Published in: Advances in Information Retrieval - 41st European Conference on IR Research, ECIR 2019, Cologne, Germany, April 14–18, 2019, Proceedings, Part I, Issue 11437, 2019, Page(s) 523-538
DOI: 10.1007/978-3-030-15712-8_34