基于语境的语义排歧方法

本文针对英汉机器翻译系统(ECMT)中的语义排歧问题,提出了一种根据单词与语境之间的关系以消除单词语义歧义的模型。该模型利用反映单词之间语义共现关系的知识库词典,对有歧义的单词作出排歧。为提高知识库的覆盖率,本模型在对大量语料进行分析的基础上建立起单词语义分类之间的相关程度矩阵,同时采用动态链表来表示和维护语境,给出了寻找歧义单词的最可能的语义的排歧算法。开放测试的实验结果表明本方法使语义排歧的正确率提高约10%。

Word Sense Tagging Method Based on Context

This paper proposes a word sense disambiguating model,which is based on the word's semantic context.The model utilizes the knowledge dictionary that reflects the semantic concurrence information of English words.And the correlation of word semantic marks is obtained through statistical analysis of large real corpus.By evaluating each possible semantic context word,the most reasonable sense of the sense ambiguous word is selected.The experiment of this method proves an increase of 10% in precision.