Sentence Similarity Computational Model Based on Information Content

• Published in: IEICE Transactions on Information and Systems Vol. E99.D; no. 6; pp. 1645 - 1652
• Main Authors: WU, Hao, HUANG, Heyan
• Format: Journal Article
• Language: English; Japanese
• Published: The Institute of Electronics, Information and Communication Engineers 01.06.2016
• Subjects: Computation; inclusion-exclusion principle; information content; information retrieval; Machine translation; Mathematical models; natural language processing; Semantics; sentence semantic similarity; Sentences; Similarity; Tasks; Texts
• ISSN: 0916-8532; 1745-1361
• DOI: 10.1587/transinf.2015EDP7474

Sentence similarity computation is an increasingly important task in applications of natural language processing such as information retrieval, machine translation, text summarization and so on. From the viewpoint of information theory, the essential attribute of natural language is that the carrier of information and the capacity of information can be measured by information content which is already successfully used for word similarity computation in simple ways. Existing sentence similarity methods don't emphasize the information contained by the sentence, and the complicated models they employ often need using empirical parameters or training parameters. This paper presents a fully unsupervised computational model of sentence semantic similarity. It is also a simply and straightforward model that neither needs any empirical parameter nor rely on other NLP tools. The method can obtain state-of-the-art experimental results which show that sentence similarity evaluated by the model is closer to human judgment than multiple competing baselines. The paper also tests the proposed model on the influence of external corpus, the performance of various sizes of the semantic net, and the relationship between efficiency and accuracy.