Akira Kumano

Building an MT dictionary from parallel texts based on linguistic and statistical information

A method for generating a machine translation (MT) dictionary from parallel texts is described. This method utilizes both statistical information and linguistic information to obtain corresponding words or phrases in parallel texts. By combining these two types of information, translation pairs which cannot be obtained by a linguistic-based method can be extracted. Over 70% accurate translations of compound nouns and over 50% of unknown words are obtained as the first candidate from small Japanese/English parallel texts containing severe distortions.

A comparison of query translation methods for English-Japanese cross-language information retrieval (poster abstract)

In this paper we report results of an investigation into EnglishJapanese Cross-Language Information Retrieval (CLIR) comparing a number of query translation methods. Results from experiments using the standard BMIR-J2 Japanese collection suggest that full machine translation (MT) can outperform popular dictionary-based query translation methods and further that in this context MT is largely robust to queries with little linguistic structure.

Machine Translation vs. Dictionary Term Translation - a Comparison for English-Japanese News Article Alignment

Bilingual news article alignment methods based on multi-lingual information retrieval have been shown to be successful for the automatic production of so-called noisy-parallel corpora. In this paper we compare the use of machine translation (MT) to the commonly used dictionary term lookup (DTL) method for Reuter news article alignment in English and Japanese. The results show the trade-off between improved lexical disambiguation provided by machine translation and extended synonym choice provided by dictionary term lookup and indicate that MT is superior to DTL only at medium and low recall levels. At high recall levels DTL has superior precision.

Improvement in customizability using translation templates

This paper outlines customization of a machine translation system using translation templates, which enable users to represent the bilingual knowledge needed for complex translation. To evaluate their effectiveness, we analyzed a bilingual text to estimate the improvement in customizability. The result shows that about 60% of mistranslated sentences can be translated as model translations by combining the proposed framework with the conventional customizing functions.

Generating transliteration rules for cross-language information retrieval from machine translation dictionaries

This paper describes a method for automatically converting existing English-Japanese and Japanese-English machine translation dictionaries into English-Japanese transliteration rules and Japanese-English back-transliteration rules for cross language information retrieval. An existing English-katakana word alignment module, which is part of our own machine translation system, is exploited in generating probabilistic rewriting rules. If our system is allowed to output 15 candidate spellings, it successfully transliterates more than 75% of a set of out-of-vocabulary English words into katakana, and successfully back-transliterates more than 55% of a set of out-of-vocabulary katakana words into English. Moreover, our preliminary cross-language information retrieval experiments, which treat the candidate spellings as a group of synonyms, suggest that our methods can indeed compensate for the failure of machine translation in some cases.