@inproceedings{fung-1998-statistical,
title = "A statistical view on bilingual lexicon extraction",
author = "Fung, Pascale",
booktitle = "Proceedings of the Third Conference of the Association for Machine Translation in the Americas: Technical Papers",
month = oct # " 28-31",
year = "1998",
address = "Langhorne, PA, USA",
publisher = "Springer",
url = "https://link.springer.com/chapter/10.1007/3-540-49478-2_1",
pages = "1--17",
abstract = "We present two problems for statistically extracting bilingual lexicon: (1) How can noisy parallel corpora be used? (2) How can non-parallel yet comparable corpora be used? We describe our own work and contribution in relaxing the constraint of using only clean parallel corpora. DKvec is a method for extracting bilingual lexicons, from noisy parallel corpora based on arrival distances of words in noisy parallel corpora. Using DKvec on noisy parallel corpora in English/Japanese and English/Chinese, our evaluations show a 55.35{\%} precision from a small corpus and 89.93{\%} precision from a larger corpus. Our major contribution is in the extraction of bilingual lexicon from non-parallel corpora. We present a first such result in this area, from a new method-Convec. Convec is based on context information of a word to be translated.",
}
Markdown (Informal)
[A statistical view on bilingual lexicon extraction](https://link.springer.com/chapter/10.1007/3-540-49478-2_1) (Fung, AMTA 1998)
ACL