Synonymous Collocation Extraction Using Translation Information

Synonymous Collocation Extraction Using Translation Information Hua WU, Ming ZHOU Microsoft Research Asia 5F Sigma Center, No.49 Zhichun Road, Haidian District Beijing, 100080, China wu_hua_@msn.com, mingzhou@microsoft.com Abstract Automatically acquiring synonymous col- location pairs such as <turn on, OBJ, light> and <switch on, OBJ, light> from corpora is a challenging task. For this task, we can, in general, have a large monolingual corpus and/or a very limited bilingual corpus. Methods that use monolingual corpora alone or use bilingual corpora alone are apparently inadequate because of low pre- cision or low coverage. In this paper, we propose a method that uses both these re- sources to get an optimal compromise of precision and coverage. This method first gets candidates of synonymous collocation pairs based on a monolingual corpus and a word thesaurus, and then selects the ap- propriate pairs from the candidates using their translations in a second language. The translations of the candidates are obtained with a statistical translation model which is trained with a small bilingual corpus and a large monolingual corpus. The translation information is proved as effective to select synonymous collocation pairs. Experi- mental results indicate that the average precision and recall of our approach are 74% and 64% respectively, which outper- form those methods that only use mono- lingual corpora and those that only use bi- lingual corpora. 1 Introduction This paper addresses the problem of automatically extracting English synonymous collocation pairs using translation information. A synonymous col- location pair includes two collocations which are similar in meaning, but not identical in wording. Throughout this paper, the term collocation refers to a lexically restricted word pair with a certain syntactic relation. For instance, <turn on, OBJ, light> is a collocation with a syntactic relation verb-object, and <turn on, OBJ, light> and <switch on, OBJ, light> are a synonymous collocation pair. In this paper, translation information means trans- lations of collocations and their translation prob- abilities. Synonymous collocations can be considered as an extension of the concept of synonymous ex- pressions which conventionally include synony- mous words, phrases and sentence patterns. Syn- onymous expressions are very useful in a number of NLP applications. They are used in information retrieval and question answering (Kiyota et al., 2002; Dragomia et al., 2001) to bridge the expres- sion gap between the query space and the document space. For instance, “buy book” extracted from the users’ query should also in some way match “order book” indexed in the documents. Besides, the synonymous expressions are also important in language generation (Langkilde and Knight, 1998) and computer assisted authoring to produce vivid texts. Up to now, there have been few researches which directly address the problem of extracting synonymous collocations. However, a number of studies investigate the extraction of synonymous words from monolingual corpora (Carolyn et al., 1992; Grefenstatte, 1994; Lin, 1998; Gasperin et al., 2001). The methods used the contexts around the investigated words to discover synonyms. The problem of the methods is that the precision of the extracted synonymous words is low …

Content truncated to 500 words