Chiao Yun-Chuang, Zweigenbaum Pierre
STIM/DSI, Assistance Publique-Hôpitaux de Paris, France.
Stud Health Technol Inform. 2003;95:397-402.
We present a method, based on the similarity of word distribution across languages, of finding 'new' words' translations in French-English comparable medical texts, starting from a partial bilingual medical lexicon. In this paper, we test the influence of adding general-language words to this initial lexicon. Our experimental results show that all test words are correctly translated within the top 25 candidates; and that the addition of general words to the lexicon helps to improve translation accuracy for medical words.
我们提出了一种基于跨语言单词分布相似性的方法，该方法从部分双语医学词汇表出发，在法英可比医学文本中查找“新”单词的翻译。在本文中，我们测试了向这个初始词汇表中添加通用语言单词的影响。我们的实验结果表明，所有测试单词在前25个候选词中都能得到正确翻译；并且向词汇表中添加通用单词有助于提高医学单词的翻译准确性。
