A translation aid system by retrieving bilingual news database

Abstract

SUMMARYMachine translation technology is currently incapable of producing translations of the high quality required for purposes such as broadcast news. Such translations still require skilled human translators. We have developed a translation aid system to support translators in such tasks. The system retrieves news articles by answering user queries, and shows the entire article together with the corresponding translated article. The system does not require manual alignment of each sentence with its translation when storing articles in a database. Thus, it is capable of handling flexible translations. Moreover, the system helps users learn not just the translations for queried expressions, but also the facts described in the articles, which can aid in producing good translations. The results of a user inquiry demonstrated the validity of the system.

Retrieving meaning-equivalent sentences for example-based rough translation

“…However, recall is more highly weighted than precision in TM, while recall and precision should be equally considered in our method. To carry out wide coverage retrieval, TM relaxed various conditions on inputs: Preserving only mono-gram and bi-gram on words/characters (Baldwin, 2001;Sato, 1992), removing functional words (Kumano et al, 2002;Wakita et al, 2000), and removing content words (Sumita and Tsutsumi, 1988). In our method, information on functional words is removed and that on modality and tense is introduced instead.…”

Construction and analysis of Japanese-English broadcast news corpus with named entity tags

“…The original Japanese article and the translated English article deal with the same topic, but they differ much in details. The difference arises from the following reasons (Kumano et al, 2002). Audience Content might be added or deleted, according to the audience, especially for international broadcasting.…”

“…For this research, we obtained a Japanese-English broadcast news corpus (Kumano et al, 2002) by the Japanese broadcast company NHK 3 , and we are manually tagging NEs in the corpus to analyze it and to conduct NE translation-pair extraction experiments.…”

Construction of English composition support system based on conveying emotion

“…To improve the ability of English sentence composition we thought that it was important for the learners to become able to select the exact or close English sentence describing what the learner wants to say from the large amount of example sentences. The research focusing on English composition support based on example sentences and the retrieval method for the example sentences have been already studied [5], [6], [7]. However, the traditional example sentence retrieval methods usually only dealt with the superficial or semantic similarity of the sentences.…”