Yasutsugu Morimoto

Learning translation templates from bilingual text

This paper proposes a two-phase example-based machine translation methodology which develops translation templates from examples and then translates using template matching. This method improves translation quality and facilitates customization of machine translation systems. This paper focuses on the automatic learning of translation templates. A translation template is a bilingual pair of sentences in which corresponding units (words and pharases) are coupled and replaced with variables. Correspondence between units is determined by suing a bilingual dictionary and by analyzing the syntactic structure of the sentences. Syntactic ambiguity and ambiguity in correspondence between units are simultaneously resolved. All of the translation templates generated from a bilingual corpus are grouped by their source language part, and then further refined to resolved conflicts among templates whose source language parts are the same but whose target language parts are different. By using the proposed method, not only transfer rules but also knowledge for lexical selection is effectively extracted from a bilingual corpus.

Unsupervised word sense disambiguation using bilingual comparable corpora

An unsupervised method for word sense disambiguation using a bilingual comparable corpus was developed. First, it extracts statistically significant pairs of related words from the corpus of each language. Then, aligning pairs of related words translingually, it calculates the correlation between the senses of a first-language polysemous word and the words related to the polysemous word, which can be regarded as clues for determining the most suitable sense. Finally, for each instance of the polysemous word, it selects the sense that maximizes the score, i.e., the sum of the correlations between each sense and the clues appearing in the context of the instance. To overcome both the problem of ambiguity in the translingual alignment of pairs of related words and that of disparity of topical coverage between corpora of different languages, an algorithm for calculating the correlation between senses and clues iteratively was devised. An experiment using Wall Street Journal and Nihon Keizai Shimbun corpora showed that the new method has promising performance; namely, the applicability and precision of its sense selection are 88.5% and 77.7%, respectively, averaged over 60 test polysemous words.

Corpus-dependent association thesauri for information retrieval

This paper presents a method for automatically generating an association thesaurus from a text corpus, and demonstrates its application to information retrieval. The thesaurus generation method consists of extracting terms and co-occurrence data from a corpus and analyzing the correlation between terms statistically. A new method for disambiguating the structure of compound nouns, which is a key component for term extraction, is also proposed. The automatically generated thesaurus is effectively used as a tool for exploring information. A thesaurus navigator having novel functions such as term clustering, thesaurus overview, and zooming-in is proposed.