High-risk learning: acquiring new word vectors from tiny data

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Herbelot, Aurélie
• dc.contributor.author Baroni, Marco
• dc.date.accessioned 2020-12-10T09:39:24Z
• dc.date.available 2020-12-10T09:39:24Z
• dc.date.issued 2018
• dc.description Comunicació presentada a: 2017 Conference on Empirical Methods in Natural Language Processing celebrat del 7 al 11 de setembre de 2017 a Copenhaguen, Dinamarca.
• dc.description.abstract Distributional semantics models are known to struggle with small data. It is generally accepted that in order to learn ‘a good vector’ for a word, a model must have sufficient examples of its usage. This contradicts the fact that humans can guess the meaning of a word from a few occurrences only. In this paper, we show that a neural language model such as Word2Vec only necessitates minor modifications to its standard architecture to learn new terms from tiny data, using background knowledge from a previously learnt semantic space. We test our model on word definitions and on a nonce task involving 2-6 sentences’ worth of context, showing a large increase in performance over state-of-the-art models on the definitional task.en
• dc.description.sponsorship We acknowledge ERC 2011 Starting Independent Research Grant No 283554 (COMPOSES). This project has also received funding from the European Union’s Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement No 751250.
• dc.format.mimetype application/pdf
• dc.identifier.citation Herbelot A, Baroni M. High-risk learning: acquiring new word vectors from tiny data. In: Palmer M, Hwa R, Riedel S, editors. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing; 2017 Sep 7-11; Copenhagen, Denmark. Stroudsburg (PA). Association for Computational Linguistics; 2017. p. 304–9. DOI: 10.18653/v1/D17-1030
• dc.identifier.doi http://dx.doi.org/10.18653/v1/D17-1030
• dc.identifier.uri http://hdl.handle.net/10230/45966
• dc.language.iso eng
• dc.publisher ACL (Association for Computational Linguistics)
• dc.relation.ispartof Palmer M, Hwa R, Riedel S, editors. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing; 2017 Sep 7-11; Copenhagen, Denmark. Stroudsburg (PA). Association for Computational Linguistics; 2017. p. 304–9
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/751250
• dc.relation.projectID info:eu-repo/grantAgreement/EC/FP7/283554
• dc.rights © ACL, Creative Commons Attribution 4.0 License (https://creativecommons.org/licenses/by/4.0/)
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.rights.uri https://creativecommons.org/licenses/by/4.0/
• dc.title High-risk learning: acquiring new word vectors from tiny dataen
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion