Abstract

We present a pattern matching method for compiling a bilingual lexicon of nouns and proper nouns from unaligned, noisy parallel texts of Asian/IndcEuropean language pairs. Tagging information of one guage is used. Word frequency and position information for high and low frequency words are represented in two different vector forms for pattern matching. New anchor point finding and noise elimination techniques are introduced. We obtained a 73.1% precision. We also show how the results can be used in the compilation of domain-specific noun phrases.

Citations

149	Aligning Sentences in Parallel Corpora - Brown - 1991
115	Text-translation alignment - Kay, Röscheisen - 1993
103	Char align: A Program for Aligning Parallel Texts at the Character Level - Church - 1993
99	Aligning Sentences in Bilingual Corpora Using Lexical Information - Chen - 1993
98	An algorithm for finding noun phrase correspondences in bilingual corpora - Kupiec - 1993
69	Kvec: A new approach for aligning parallel texts - FUNG, CHURCH - 1994
64	Robust bilingual word alignment for machine aided translation - Dagan, Church, et al. - 1993
63	Aligning a parallel English-Chinese corpus statistically with lexical criteria - WU - 1994
41	Statistical augmentation of a Chinese machine-readable dictionary - Fung, Wu - 1994
35	Aligning noisy parallel corpora across language groups: Word pair feature matching by dynamic time warping - FUNG, McKEOWN - 1994
30	Building an MT Dictionary from Parallel Texts Based on Linguistic and Statistical - Kumano, Hirakawa - 1994
9	Aligning parallel texts: Do methods developed for English-French generalize to Asian languages - CHURCH, DAGAN, et al. - 1993
9	Translating collocations for use in bilingual lexicons - SMADJA, McKEOWN - 1994
4	TextTranslation alignment - oscheisen - 1993