한국어 단어 임베딩 모델의 평가에 적합한 유추 검사 세트

목차 (Table of Contents)

• 요약
• Abstract
• Ⅰ. 서론
• Ⅱ. Word2vec 모델 및 유추 검사
• Ⅲ. 한국어 단어 임베딩 모델에 적합한 유추 검사 방안
• Ⅳ. 한국어 유추 검사 세트의 적용 – 한국어 형태소 분석기의 성능 비교
• Ⅴ. 결론
• 참고문헌

참고문헌 (Reference)

1 이동준, "형태소 기반 효율적인 한국어 단어 임베딩" 한국정보과학회 45 (45): 444-450, 2018

2 Wikipedia, "Word Embedding [Internet]"

3 M. Sahlgren, "The distributional hypothesis" 20 : 33-53, 2008

4 Hyungsuc Kang, "Selection of the Optimal Morphological Analyzer for a Korean Word2vec Model" 2018

5 T. Young, "Recent trends in deep learning based natural language processing" 13 (13): 55-75, 2018

6 L. Finkelstein et al., "Placing Search in Context: The Concept Revisited" 20 (20): 116-131, 2002

7 Sanghyuk Choi, "On Word Embedding Models and Parameters Optimized for Korean" 252-256, 2016

8 Eunjeong L. Park, "KoNLPy: Korean natural language processing in Python" 133-136, 2014

9 Eunjeong L. Park, "KoNLPy: Korean NLP in Python [Internet]"

10 Siwei Lai, "How to generate a good word embedding" 31 (31): 5-14, 2016

11 T. Schnabel, "Evaluation methods for unsupervised word embeddings" 298-307, 2015

12 T. Mikolov, "Efficient estimation of word representations in vector space"

13 M. Baroni, "Don't count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors" 1 : 238-247, 2014

14 T. Mikolov, "Distributed representations of words and phrases and their compositionality" 3111-3119, 2013

15 A. Gladkova, "Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn't" 8-15, 2016

16 ACL(Association for Computational Linguistics) Wiki, "Analogy (State of the art) [Internet]"

17 R. M. Kaplan, "A method for tokenizing text, Inquiries into words, constraints and contexts" 55-64, 2005