래티스상의 구조적 분류에 기반한 한국어 형태소 분석 및 품사 태깅 = Lattice-based Discriminative Approach for Korean Morphological Analysis

국문 초록 (Abstract)

본 논문에서는 래티스상의 구조적 분류에 기반한 한국어 형태소 분석 및 품사 태깅을 수행하는 방법을 제안한다. 제안하는 방법은 입력문이 주어질 때 어휘 사전(lexicon)을 참조하여, 형태소를 노드로 취하고 인접형태소간의 에지를 갖도록 래티스를 구성하며, 구성된 래티스상 가장 점수가 높은 경로상에 있는 형태소들을 분석 결과로 제시하는 방법이다. 실험 결과, ETRI 품사 부착 코퍼스에서 기존의 1차 linear-chain CRF에 기반한 방법보다 높은 어절 정확률 그리고 문장 정확률을 얻었다.

다국어 초록 (Multilingual Abstract)

In this paper, we propose a lattice-based discriminative approach for Korean morphological analysis and POS tagging. In our approach, for an input sentence, a morpheme lattice is first created from a lexicon where each node corresponds to a morpheme in the lexicon and each edge is formed between two consecutive morphemes. A candidate result of morphological analysis is then represented as a path in the morpheme lattice which is defined as the sequence of edges, starting in the initial state and ending with the final state. In this setting, the morphological analysis is simply considered as the process of finding the best path among all possible paths. Experiment results show that the proposed lattice-based method outperforms the first-order linear-chain CRF.

목차 (Table of Contents)

• 요약
• Abstract
• 1. 서론
• 2. 관련 연구
• 3. 래티스상 구조적 분류에 기반한 한국어 형태소 분석
• 4. 실험 결과
• 5. 결론 및 향후 연구 방향
• References

참고문헌 (Reference)

1 심광섭, "형태소 분석기 사용을 배제한 음절 단위의 한국어 품사 태깅" 한국인지과학회 22 (22): 327-345, 2011

2 이재성, "한국어 형태소 분석을 위한 3단계 확률 모델" 한국정보과학회 38 (38): 257-268, 2011

3 심광섭, "인접 조건 검사에 의한 초고속 한국어 형태소 분석" 한국정보과학회 31 (31): 89-99, 2004

4 심광섭, "음절 단위의 한국어 품사 태깅에서 원형 복원" 한국정보과학회 40 (40): 182-189, 2013

5 신준철, "기분석 부분 어절 사전을 활용한 한국어 형태소 분석기" 한국정보과학회 39 (39): 415-424, 2012

6 S.-H. Na, "Two-Stage Compound Morpheme Segmentation in CRF-based Korean Morphological Analysis" 13-17, 2013

7 E.-C. Lee, "The Implementation of Korean morphological Analyzer Using Hierarchical Symbolic Connectivity Information" 95-104, 1992

8 Lee, G. G, "Syllable-Pattern-Based Unknown- Morpheme Segmentation and Estimation for Hybrid Part-of-Speech Tagging of Korean" 28 (28): 2002

9 S.-H. Na, "Semi-CRF or Linear-chain CRF? A Comparative Study of Joint Models for Korean Morphological Analysis and POS Tagging" 9-12, 2013

10 Lee, D, "Probabilistic Models for Korean Morphological Analysis" 197-202, 2005

11 Mcdonald, R., "Online Large-Margin Training of Dependency Parsers" 91-98, 2005

12 S.-S. Kang, "Multi-level Morphology and Morphological Analysis Model for Korean" 140-145, 1994

13 S.-I. Yang, "Morphological Analysis for Korean Compounded Morpheme Using Whiter Space Information" 612-616, 2001

14 Shim, K., "MACH - A Supersonic Korean Morphological Analyzer" 939-945, 2002

15 Freund, Y., "Large Margin Classification Using the Perceptron Algorithm" 37 (37): 277-296, 1999

16 O.-W. Kwon, "Korean Morphological Analyzer and Part-of-Speech Tagger Based on CYK Algorithm Using Syllable Information" 76-88, 1999

17 S.-S. Kang, "Korean Morphological Analysis and Information Retrieval" Hongrung publishing company 2002

18 C. Lee, "Joint Models for Korean Word Spacing and POS Tagging using Structural SVM" 604-606, 2013

19 Collins, M, "Discriminative Traning Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms" 1-8, 2002

20 S.-H. Yeo, "Design and Implementation of an Effective Morphological Analyzer with Multi - level Filtering competence" 797-800, 1991

21 N. Nam, "Comparisons of sequence labeling algorithms and extensions" 681-688, 2007

22 S.-H. Na, "CRFs for Korean Morpheme Segmentation and POS Tagging" 12-15, 2012

23 Kudo, T., "Applying Conditional Random Fields to Japanese Morphological Analysis" 230-237, 2004

24 J.-H. Choi, "A method for reducing dictionary access with bidirectional longest match strategy in Korean morphological analyzer" 20 (20): 1497-1507, 1993

25 S.-J. Lee, "A Two-Level Approach to Korean Verb Morphology" 993-996, 1992

26 J.-P. Hong, "A New Korean Morphological Analyzer using Eojeol Pattern Dictionary" 279-284, 2008

27 S.-S. Kang, "A General Morphological Analyzer and Spelling Checker for the Korean Language Using Syllable Characteristics" 23 (23): 530-539, 1996