【摘要】 双语语料自动对齐是自然语言处理的一个重要研究课题。该文针对基于词典译文的英汉句子对齐算法存在的缺点,提出了面向小词典的高效英汉句子对齐算法,该算法在小词典的情况下仍具有较高的准确率,效率比传统算法提高近一倍。通过理论分析、对比实验可知,该算法是有效的。更多还原

【Abstract】 Automatic alignment of parallel corpora is an important research subject in natural language processing area.An efficient small-dictionary-oriented algorithm for alignment of English-Chinese parallel corpora is proposed in this paper in order to improve the efficiency of translation-based approach to parallel corpora alignment,and enhance its precision when the dictionary used is small.The algorithm has competitive precision under the condition of small dictionary,and doubles the efficiency of the traditional approach.The validity of the algorithm is argued through theoretical analysis and experiments.更多还原