DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Myaeng, Sung-Hyon | - |
dc.contributor.advisor | 맹성현 | - |
dc.contributor.author | Mussakhojayeva, Saida | - |
dc.date.accessioned | 2021-05-11T19:34:23Z | - |
dc.date.available | 2021-05-11T19:34:23Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=875476&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/283100 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2019.8,[iv, 34 p. :] | - |
dc.description.abstract | In this work we address the problem of creating relational word-pair embeddings, which represent relations between word pairs as a compositional function between two words. Word-pair embeddings are useful for downstream NLP tasks, such as NLI, where knowledge about a relation between individual words is critical in inferring a relation between two pieces of text. We propose a novel method for limiting pairs to those in close proximity as a way of reducing the computation time significantly while maintaining or improving the quality. In addition, we propose to incorporate external knowledge from hierarchical sources (such as WordNet) alongside such embeddings so that not only syntagmatic relations but also paradigmatic relations are reflected. We test the proposed methods with MNLI and FEVER datasets. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Natural language inference▼aunsupervised pre-training▼aword-pair embeddings | - |
dc.subject | 자연어추론▼a비지도 사전학습▼a단어쌍 임베딩 | - |
dc.title | Relational word-pair embeddings for natural language inference | - |
dc.title.alternative | 자연어추론을 위한 관계기반 단어쌍 임베딩 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 뮤사호드자예바 세이다 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.