DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jang, Kyoungrok | ko |
dc.contributor.author | Myaeng, Sung-Hyon | ko |
dc.contributor.author | Kim, Sang-Bum | ko |
dc.date.accessioned | 2023-07-05T01:01:01Z | - |
dc.date.available | 2023-07-05T01:01:01Z | - |
dc.date.created | 2023-06-08 | - |
dc.date.issued | 2018-11-01 | - |
dc.identifier.citation | 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018, pp.341 - 343 | - |
dc.identifier.uri | http://hdl.handle.net/10203/310301 | - |
dc.description.abstract | In this paper, we propose a method of calibrating a word embedding, so that the semantic it conveys becomes more relevant to the context. Our method is novel because the output shows clearly which senses that were originally presented in a target word embedding become stronger or weaker. This is possible by utilizing the technique of using sparse coding to recover senses that comprises a word embedding. | - |
dc.language | English | - |
dc.publisher | Association for Computational Linguistics (ACL) | - |
dc.title | Interpretable Word Embedding Contextualization | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85079041606 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 341 | - |
dc.citation.endingpage | 343 | - |
dc.citation.publicationname | 2018 Conference on Empirical Methods in Natural Language Processing, EMNLP 2018 | - |
dc.identifier.conferencecountry | BE | - |
dc.identifier.conferencelocation | Brussels | - |
dc.contributor.localauthor | Myaeng, Sung-Hyon | - |
dc.contributor.nonIdAuthor | Kim, Sang-Bum | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.