基于字符级特征的日文依存句法自动分析算法.pdf

40 4 () Vol.40 No .4 2009 8 Journal of Central South University (Science and Technology) Aug. 2009 1, 4 2, 3 4 4 (1. 410082 2. 999077 3. 215006 4. 410208) 2 1 2 3 1 2 CoNLL-2009 UAS () LAS () TP391 A 1672−7207(2009)04−1035−05 Japanese dependency parsing based on character-level features 1, 4 2, 3 4 4 WEN Yi-min , ZHAO Hai , LI Jian , HUANG Han-wen (1.College of Electrical and Information Engineering, Hunan University, Changsha 410082, China; 2. Department of Chinese Translation and Linguistics, City University of Hongkong, Hongkong 999077, China; 3. School of Computer Science and Technology, Soochow University, Suzhou 215006, China; 4. Department of Information Engineering, Hunan Industry Polytechnic, Changsha 410208, China) Abstract: Based on the indicative impact of character located at a special position in a word, an algorithm was proposed to make use of character-level features that reflect the characteristics of Japanese to enhance the performance of Japanese dependency parsing. Three character-level features denoted by the first two characters, the last character, and the last two characters inside a word were adopted. The first type of features was used for the morphological purpose, and the la