基于条件随机场的冠词选择研究

冠词选择需要综合考虑语言知识、语义知识以及世界知识,是汉英翻译中的一个难点。针对传统的基于规则和机器学习的方法,只考虑名词短语前冠词选择的问题,该文将冠词看作一种标记,将该问题形式化地描述为一个序列标注任务,提出一种基于条件随机场的解决策略,选取特征时充分利用词、词性等多层次资源,并引入前后词的互信息。实验采用包含91 106个冠词的专利摘要做测试语料,F值达到80%。

Research on Article Choice Based on Conditional Random Fields

Article choice is a difficult problem for Chinese to English translation since it involves complex knowledge about grammar,semantics and the world.Traditional researches based on rule or machine learning only deal with articles used in the noun phrases.This paper considers the article as a label and hence treats the problem as a sequence labeling task,proposing a strategy based on Conditional Random Fields.In the process of feature extraction,the proposed method makes good use of the word and part-of-speech,especially the mutual information feature.Experimental results on testing corpus composed of patent abstracts containing 91 106 articles show that the algorithm yields F-score of 80%.