지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학위논문
- 저자정보
- 발행연도
- 2018
- 저작권
- 서울대학교 논문은 저작권에 의해 보호받습니다.
이용수0
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Word embedding is a strategy of mapping each word from a continuous vector space into one vector. It is the starting point of natural language processing task and greatly impacts the performance. Word2vec and Glove are among the most popular and widely used word embedding models. However, these models have limitations in that it is unable to learn the shared structure of words nor sub-word meanings. This is a serious limitation for morphologically rich languages such as Korean.
In this paper, we propose a new model which is an expansion of the previous skip-gram model to learn the sub-word information. The model defines each word vector as a sum of its morpheme vectors and hence, learns the vectors of morphemes. To test the efficiency of our embedding, we conducted a word similarity test and a word analogy test. Furthermore, by using our trained vectors as an input to the previous text classification model, we tested how much performance has actually been enhanced.
In this paper, we propose a new model which is an expansion of the previous skip-gram model to learn the sub-word information. The model defines each word vector as a sum of its morpheme vectors and hence, learns the vectors of morphemes. To test the efficiency of our embedding, we conducted a word similarity test and a word analogy test. Furthermore, by using our trained vectors as an input to the previous text classification model, we tested how much performance has actually been enhanced.
목차
I. Introduction 1II. RelatedWorks 42.1 Skip-gram model[1] 42.2 Limitations of the skip-gram model 62.3 Existing study on Korean word embedding 8III. Morpheme-based word embedding model 9IV. Experiments 124.1 Training Corpus and Implementation Details 124.2 Evaluation Methods 124.3 Intrinsic Evaluation 134.3.1 Word Similarity Test 134.3.2 Word Analogy Test 154.3.3 Morpheme Vectors Visualization 164.4 Extrinsic Evaluation 18V. Conclusion 21References 22Appendix 24초록 25
최근 본 자료
댓글(0)
0