{"type":"ScholarlyArticle","title":"MuLaN: Multilingual Label propagatioN for Word Sense Disambiguation","authors":[{"name":"Edoardo Barba","slug":"edoardo-barba","given":"Edoardo","family":"Barba","affiliation":"Sapienza NLP Group , Department of Computer Science , Sapienza University of Rome"},{"name":"Luigi Procopio","slug":"luigi-procopio","given":"Luigi","family":"Procopio","affiliation":"Sapienza NLP Group , Department of Computer Science , Sapienza University of Rome"},{"name":"Niccolò Campolungo","slug":"niccolo-campolungo","given":"Niccolò","family":"Campolungo","affiliation":"Sapienza NLP Group , Department of Computer Science , Sapienza University of Rome"},{"name":"Tommaso Pasini","slug":"tommaso-pasini","given":"Tommaso","family":"Pasini","affiliation":"Sapienza NLP Group , Department of Computer Science , Sapienza University of Rome"},{"name":"Roberto Navigli","slug":"roberto-navigli","given":"Roberto","family":"Navigli","affiliation":"Sapienza NLP Group , Department of Computer Science , Sapienza University of Rome"}],"abstract":"The knowledge acquisition bottleneck strongly affects the creation of multilingual sense-annotated data, hence limiting the power of supervised systems when applied to multilingual Word Sense Disambiguation. In this paper, we propose a semi-supervised approach based upon a novel label propagation scheme, which, by jointly leveraging contextualized word embeddings and the multilingual information enclosed in a knowledge base, projects sense labels from a high-resource language, i.e., English, to lower-resourced ones. Backed by several experiments, we provide empirical evidence that our automatically created datasets are of a higher quality than those generated by other competitors and lead a supervised model to achieve state-of-the-art performances in all multilingual Word Sense Disambiguation tasks. We make our datasets available for research purposes at https://github.com/SapienzaNLP/mulan.","doi":"10.24963/ijcai.2020/531","url":"https://ijcai.org/proceedings/2020/531","pdf":"https://ijcai.org/proceedings/2020/0531.pdf","markdown":"https://ijcai.org/proceedings/2020/531.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/531","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Natural Language Processing","track":"Main track","number":531,"pages":{"first":3837,"last":3844},"keywords":["Natural Language Processing: Resources and Evaluation","Natural Language Processing: Natural Language Semantics"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24690/file_24690.m3u8","length_sec":293,"provider":"hls"}],"references":[{"position":1,"raw":"[Agirre et al., 2014] Eneko Agirre, Oier Lopez de Lacalle, and Aitor Soroa. Random walks for knowledge-based word sense disambiguation. Computational Linguistics, 40(1):57-84, 2014.","title":"Random walks for knowledge-based word sense disambiguation","authors":"Eneko Agirre, Oier Lopez De Lacalle, Aitor Soroa","year":"2014","venue":"Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Artetxe and Schwenk, 2019] Mikel Artetxe and Holger Schwenk. Margin-based parallel corpus mining with mul- tilingual sentence embeddings. In Proc. of ACL, pages 3197-3203, 2019.","title":"Margin-based parallel corpus mining with multilingual sentence embeddings","authors":"Artetxe, Schwenk, Mikel Artetxe, Holger Schwenk","year":"2019","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bevilacqua and Navigli, 2020] Michele Bevilacqua and Roberto Navigli. Breaking through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information. In Proc. of ACL, 2020.","title":"Breaking through the 80% Glass Ceiling: Raising the State of the Art in Word Sense Disambiguation by Incorporating Knowledge Graph Information","authors":"Michele Bevilacqua, Roberto Navigli","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Camacho-Collados et al., 2016] José Camacho-Collados, Claudio Delli Bovi, Alessandro Raganato, and Roberto Navigli. A Large-Scale Multilingual Disambiguation of Glosses. In Proc. of LREC, pages 1701-1708, 2016.","title":"A Large-Scale Multilingual Disambiguation of Glosses","authors":"Camacho-Collados","year":"2016","venue":"Proc. of LREC","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Conneau and Lample, 2019] Alexis Conneau and Guil- laume Lample. Cross-lingual language model pretraining. In Advances in NeurIPS, pages 7059-7069. 2019.","title":"Alexis Conneau and Guillaume Lample. Cross-lingual language model pretraining","authors":"Lample Conneau","year":"2019","venue":"Advances in NeurIPS","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Conneau et al., 2019] Alexis Conneau, Kartikay Khandel- wal, Naman Goyal, Vishrav Chaudhary, Guillaume Wen- zek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. Unsupervised cross- lingual representation learning at scale. In arXiv preprint arXiv:1911.02116, 2019.","title":"Unsupervised crosslingual representation learning at scale","authors":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, Veselin Stoyanov","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Delli Bovi et al., 2017] Claudio Delli Bovi, Jose Camacho- Collados, Alessandro Raganato, and Roberto Navigli. Eu- rosense: Automatic harvesting of multilingual sense an- notations from parallel text. In Proc. of ACL, volume 2, pages 594-600, 2017.","title":"Eurosense: Automatic harvesting of multilingual sense annotations from parallel text","authors":"Claudio Delli Bovi, Jose Camacho-Collados, Alessandro Raganato, Roberto Navigli","year":"2017","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Devlin et al., 2019] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. BERT: Pre-training of deep bidirectional transformers for language understand- ing. In Proc. of NAACL, pages 4171-4186, June 2019.","title":"BERT: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2019","venue":"Proc. of NAACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Huang et al., 2019] Luyao Huang, Chi Sun, Xipeng Qiu, and Xuan-Jing Huang. GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge. In Proc. of EMNLP-IJCNLP, pages 3500-3505, 2019.","title":"GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge","authors":"Huang","year":"2019","venue":"Proc. of EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Johnson et al., 2019] Jeff Johnson, Matthijs Douze, and Hervé Jégou. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 2019.","title":"Billion-scale similarity search with GPUs","authors":"Jeff Johnson, Matthijs Douze, Hervé Jégou","year":"2019","venue":"IEEE Transactions on Big Data","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Kumar et al., 2019] Sawan Kumar, Sharmistha Jat, Karan Saxena, and Partha Talukdar. Zero-shot Word Sense Dis- ambiguation using sense definition embeddings. In Proc. of ACL, pages 5670-5681, July 2019.","title":"Zero-shot Word Sense Disambiguation using sense definition embeddings","authors":"Sawan Kumar, Sharmistha Jat, Karan Saxena, Partha Talukdar","year":"2019","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Langone et al., 2004] Helen Langone, Benjamin R Haskell, and George A Miller. Annotating WordNet. In Proc. of the Workshop Frontiers in Corpus Annotation, 2004.","title":"Annotating WordNet","authors":"Helen Langone, Benjamin R Haskell, George A Miller","year":"2004","venue":"Proc. of the Workshop Frontiers in Corpus Annotation","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lefever et al., 2011] Els Lefever, Véronique Hoste, and Martine De Cock. ParaSense or how to use parallel cor- pora for Word Sense Disambiguation. In Proc. of ACL, 2011, pages 317-322, 2011.","title":"ParaSense or how to use parallel corpora for Word Sense Disambiguation","authors":"Lefever","year":"2011","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Loureiro and Jorge, 2019] Daniel Loureiro and Alípio Jorge. Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation. In Proc. of ACL, pages 5682-5691, 2019.","title":"Daniel Loureiro and Alípio Jorge. Language Modelling Makes Sense: Propagating Representations through WordNet for Full-Coverage Word Sense Disambiguation","authors":"Jorge Loureiro","year":"2019","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Maru et al., 2019] Marco Maru, Federico Scozzafava, Fed- erico Martelli, and Roberto Navigli. SyntagNet: Challeng- ing Supervised Word Sense Disambiguation with Lexical- Semantic Combinations. In Proc. of EMNLP-IJCNLP, pages 3525-3531, 2019.","title":"SyntagNet: Challenging Supervised Word Sense Disambiguation with Lexical-Semantic Combinations","authors":"Marco Maru, Federico Scozzafava, Federico Martelli, Roberto Navigli","year":"2019","venue":"Proc. of EMNLP-IJCNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[McCarthy et al., 2007] Diana McCarthy, Rob Koeling, Julie Weeds, and John Carroll. Unsupervised acquisition of pre- dominant word senses. Comput. Linguist., 33(4):553-590, 2007.","title":"Unsupervised acquisition of predominant word senses","authors":"Diana Mccarthy, Rob Koeling, Julie Weeds, John Carroll","year":"2007","venue":"Comput. Linguist","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[McNemar, 1947] Quinn McNemar. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika, 12(2):153-157, 1947.","title":"Note on the sampling error of the difference between correlated proportions or percentages","authors":"Quinn Mcnemar","year":"1947","venue":"Psychometrika","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Miller et al., 1990] George A. Miller, R.T. Beckwith, Chris- tiane D. Fellbaum, D. Gross, and K. Miller. WordNet: an online lexical database. Int. J. Lexicogr, 3(4):235-244, 1990.","title":"WordNet: an online lexical database","authors":"George A Miller, R T Beckwith, Christiane D Fellbaum, D Gross, K Miller","year":"1990","venue":"Int. J. Lexicogr","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Miller et al., 1993] George A. Miller, Claudia Leacock, Randee Tengi, and Ross Bunker. A semantic concordance. In Proc. of the Workshop on Human Language Technology, pages 303-308, Plainsboro, N.J., 1993.","title":"A semantic concordance","authors":"George A Miller, Claudia Leacock, Randee Tengi, Ross Bunker","year":"1993","venue":"Proc. of the Workshop on Human Language Technology","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Moro and Navigli, 2015] Andrea Moro and Roberto Nav- igli. SemEval-2015 Task 13: Multilingual All-Words Sense Disambiguation and Entity Linking. In Proc. of SemEval-2015, pages 288-297, 2015.","title":"SemEval-2015 Task 13: Multilingual All-Words Sense Disambiguation and Entity Linking","authors":"Andrea Moro, Roberto Navigli","year":"2015","venue":"Proc. of SemEval-2015","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Moro et al., 2014] Andrea Moro, Alessandro Raganato, and Roberto Navigli. Entity Linking meets Word Sense Dis- ambiguation: a unified approach. TACL, 2:231-244, 2014.","title":"Entity Linking meets Word Sense Disambiguation: a unified approach","authors":"Andrea Moro, Alessandro Raganato, Roberto Navigli","year":"2014","venue":"TACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Navigli and Ponzetto, 2012] Roberto Navigli and Si- mone Paolo Ponzetto. BabelNet: The automatic con- struction, evaluation and application of a wide-coverage multilingual semantic network. Artificial Intelligence, 193:217-250, 2012.","title":"BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network","authors":"Roberto Navigli, Simone Paolo, Ponzetto","year":"2012","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Navigli et al., 2013] Roberto Navigli, David Jurgens, and Daniele Vannella. SemEval-2013 task 12: Multilingual word sense disambiguation. In Proc. of SemEval-2013, volume 2, pages 222-231, 2013.","title":"SemEval-2013 task 12: Multilingual word sense disambiguation","authors":"Navigli","year":"2013","venue":"Proc. of SemEval-2013","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Navigli, 2009] Roberto Navigli. Word Sense Disambigua- tion: A survey. ACM Comput. Surveys, 41(2):1-69, 2009.","title":"Word Sense Disambiguation: A survey","authors":"Roberto Navigli","year":"2009","venue":"ACM Comput. Surveys","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Pasini and Navigli, 2017] Tommaso Pasini and Roberto Navigli. Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in Multiple Languages without Manual Training Data. In Proc. of EMNLP, pages 78-88, 2017.","title":"Train-O-Matic: Large-Scale Supervised Word Sense Disambiguation in Multiple Languages without Manual Training Data","authors":"Tommaso Pasini, Roberto Navigli","year":"2017","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Pasini and Navigli, 2020] Tommaso Pasini and Roberto Navigli. Train-O-Matic: Supervised Word Sense Disam- biguation with no (manual) effort. Artificial Intelligence, 279:103-215, 2020.","title":"Train-O-Matic: Supervised Word Sense Disambiguation with no (manual) effort","authors":"Tommaso Pasini, Roberto Navigli","year":"2020","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Pasini, 2020] Tommaso Pasini. The Knowledge Acquisition Bottleneck Problem in Multilingual Word Sense Disam- biguation. In Proc. of IJCAI, 2020.","title":"The Knowledge Acquisition Bottleneck Problem in Multilingual Word Sense Disambiguation","authors":"Tommaso Pasini","year":"2020","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2020/687"},{"position":28,"raw":"[Pilehvar and Navigli, 2014] Mohammad Taher Pilehvar and Roberto Navigli. A large-scale pseudoword-based evalu- ation framework for state-of-the-art Word Sense Disam- biguation. Comput. Linguist., 40(4):837-881, 2014.","title":"A large-scale pseudoword-based evaluation framework for state-of-the-art Word Sense Disambiguation","authors":"Mohammad Taher, Pilehvar, Roberto Navigli","year":"2014","venue":"Comput. Linguist","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Raganato et al., 2017] Alessandro Raganato, Claudio Delli Bovi, and Roberto Navigli. Neural Sequence Learning Models for Word Sense Disambiguation. In Proc. of EMNLP, pages 1156-1167, 2017.","title":"Neural Sequence Learning Models for Word Sense Disambiguation","authors":"Alessandro Raganato, Claudio Delli Bovi, Roberto Navigli","year":"2017","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Reif et al., 2019] Emily Reif, Ann Yuan, Martin Watten- berg, Fernanda B Viegas, Andy Coenen, Adam Pearce, and Been Kim. Visualizing and Measuring the Geome- try of BERT. In Advances in NeurIPS, pages 8592-8600, 2019.","title":"Visualizing and Measuring the Geometry of BERT","authors":"Emily Reif, Ann Yuan, Martin Wattenberg, Fernanda B Viegas, Andy Coenen, Adam Pearce, Been Kim","year":"2019","venue":"Advances in NeurIPS","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Scarlini et al., 2019] Bianca Scarlini, Tommaso Pasini, and Roberto Navigli. Just \"OneSeC\" for Producing Multilin- gual Sense-Annotated Data. In Proc. of ACL, pages 699- 709, 2019.","title":"Just \"OneSeC\" for Producing Multilingual Sense-Annotated Data","authors":"Bianca Scarlini, Tommaso Pasini, Roberto Navigli","year":"2019","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Scarlini et al., 2020] Bianca Scarlini, Tommaso Pasini, and Roberto Navigli. SensEmBERT: Context-Enhanced Sense Embeddings for Multilingual Word Sense Disambigua- tion. In Proc. of AAAI, 2020.","title":"SensEmBERT: Context-Enhanced Sense Embeddings for Multilingual Word Sense Disambiguation","authors":"Bianca Scarlini, Tommaso Pasini, Roberto Navigli","year":"2020","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Taghipour and Ng, 2015] Kaveh Taghipour and Hwee Tou Ng. One Million Sense-Tagged Instances for Word Sense Disambiguation and Induction. In Proc. of CoNLL, pages 338-344, 2015.","title":"One Million Sense-Tagged Instances for Word Sense Disambiguation and Induction","authors":"Ng ; ] Kaveh Taghipour, Hwee Tou Taghipour, Ng","year":"2015","venue":"Proc. of CoNLL","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Advances in NeurIPS, pages 6000-6010, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Advances in NeurIPS","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Vial et al., 2019] Loïc Vial, Benjamin Lecouteux, and Di- dier Schwab. Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation. In Proc. of GWC, 2019.","title":"Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation","authors":"Loïc Vial, Benjamin Lecouteux, Didier Schwab","year":"2019","venue":"Proc. of GWC","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Yuan et al., 2016] Dayu Yuan, Julian Richardson, Ryan Do- herty, Colin Evans, and Eric Altendorf. Semi-supervised Word Sense Disambiguation with neural models. In Proc. of COLING, pages 1374-1385, 2016.","title":"Semi-supervised Word Sense Disambiguation with neural models","authors":"Dayu Yuan, Julian Richardson, Ryan Doherty, Colin Evans, Eric Altendorf","year":"2016","venue":"Proc. of COLING","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}