Paraphrasing Of Chinese Utterances Based On The Method Of Templates

Paraphrase is a common phenomenon in natural language which captures core aspects of variability in language. The study of paraphrase is about the synonymy phenomena of phrases or sentences. With the development of foundation technology of NLP(Natural Language Progress), research on paraphrase has been recently received growing attention. Currently, paraphrasing technology has been applied in many NLP fields, such as, information retrieval, question answering, information extraction, automatic summarization and machine translation, improving the performance of these systems.This paper will mainly survey several aspects as followed: paraphrases corpus construction, paraphrases rules extraction, paraphrases generation and paraphrase evaluation. And some of our work about paraphrase is introduced in the next section. At last, some challenges, together with the future directions of paraphrasing technology are indicated.In a spoken language translation system, when the input utterance can't be successfully parsed and translated, if the system can provide the other possible expression of the input, it will be very helpful to improve the performance of the translation system. This paper introduces an approach to paraphrasing Chinese utterances. In this approach, an input utterance is first analyzed in terms of phrase structure, dependency of chunks, etc., by using multiple methods. Then, the main features of the input utterance are extracted, and the extraction results are represented by a frame. Finally, other possible expressions of the input are generated based on the analysis results by different methods.Extraction and matching of templates are the most important problems of Template-Based Paraphrasing. The extraction module extracts the sentence frame, prepositional phrase and chuck templates from the result of shallow paring. The templates are storage independently and linked by keyword-indexing in database. The match module searches the most similar template for input sentence in database, with the information of syntactic structure and lexical meaning of the sentence. The templates matching algorithm gets the searching result by using key word as the static threshold, distance and similarity score as the dynamic threshold. The method has got a good testing result.