| 摘要: |
| 词义消歧是自然语言处理中一类典型的分类问题.在分类中,特征的选择至关重要.通常情况下,特征是由人工选择的,这就要求特征选取者对于待分类的问题本身和分类模型的特点有深刻的认识.分析了汉语词义消岐中特征模板对消歧结果的影响,在此基础上提出一套基于最大熵分类模型的自动特征选择方法,包括针对所有歧义词的统一特征模板选择和针对单个歧义词的独立特征模板优化算法.实验结果表明,使用自动选择的特征,不仅简化了特征模板,而且提高了汉语词义消歧的性能.与SemEval 2007:task #5的最好成绩相比,该方法分别在微平均值MicroAve(micro-average accuracy）)和宏平均值MacroAve(macro-average accuracy）)上提升了3.10%和2.96%. |
| 关键词: 最大熵模型 分类特征 自动特征选择 汉语词义消歧 |
| DOI： |
| 分类号: |
| 基金项目:upported by the National Natural Science Foundation of China under Grant Nos.60675035, 60973053, 90920011 (国家自然科学基金); the Beijing Municipal Natural Science Foundation of China under Grant No.4072012 (北京市自然科学基金) |
|
| Chinese Word Sense Disambiguation Based on Maximum Entropy Model with Feature Selection |
|
HE Jing-Zhou,WANG Hou-Feng
|
| Abstract: |
| Word sense disambiguation (WSD) can be thought as a classification problem. Feature selection is of great importance in such a task. In general, features are selected manually, which requires a deep understanding of the task itself and the employed classification model. In this paper, the effect of feature template on Chinese WSD is studied, and an automatic feature selection algorithm based on maximum entropy model (MEM) is proposed, including uniform feature template selection for all ambiguous words and customized feature template selection for each word. Experimental result shows that automatic feature selection can reduce feature size and improve Chinese WSD performance. Compared with the best evaluation results of SemEval 2007: task #5, this method gets MicroAve (micro-average accuracy）) increase 3.10% and MacroAve (macro-average accuracy）) 2.96% respectively. |
| Key words: maximum entropy model classification feature automatic feature selection Chinese word sense disambiguation |
