Paper: Looking up phrase rephrasings via a pivot language

ACL ID W08-1911
Title Looking up phrase rephrasings via a pivot language
Venue Coling 2008: Proceedings of the workshop on Knowledge and Reasoning for Answering Questions
Year 2008

Rephrasing text spans is a common task when revising a text. However, traditional dictionaries often cannot provide direct as- sistance to writers in performing this task. In this article, we describe an approach to obtain a monolingual phrase lexicon using techniques used in Statistical Ma- chine Translation. A part to be rephrased is first translated into a pivot language, and then translated back into the origi- nal language. Models for assessing flu- ency, meaning preservation and lexical di- vergence are used to rank possible rephras- ings, and their relative weight can be tuned by the user so as to better address her needs. An evaluation shows that these models can be used successfully to select rephrasings that are likely to be useful to a writer.