Detecting Highly Confident Word Translations from Comparable Corpora without Any Prior Knowledge
Year: 2012
Type: conference-paper
Abstract: In this paper, we extend the work on using latent cross-language topic models for identifying word translations across comparable corpora. We present a novel precision oriented algorithm that relies on per-topic word distributions obtained by the bilingual LDA (BiLDA) latent topic model. The algorithm aims at harvesting only the most probable word translations across languages in a greedy fashion, without any prior knowledge about the language pair, relying on a symmetrization process and the one-to-one constraint. We report our results for Italian-English and Dutch-English language pairs that outperform the current state-of-the-art results by a significant margin. In addition, we show how to use the algorithm for the construction of high-quality initial seed lexicons of translations.
Source: Lirias
Authors: Ivan Vulić, Marie‐Francine Moens
Institution: KU Leuven
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W77273554