Work

Integrating an Unsupervised Transliteration Model into Statistical Machine Translation

Year: 2014

Type: conference-paper

Abstract: We investigate three methods for integrating an unsupervised transliteration model into an end-to-end SMT system.We induce a transliteration model from parallel data and use it to translate OOV words.Our approach is fully unsupervised and language independent.In the methods to integrate transliterations, we observed improvements from 0.23-0.75(∆ 0.41) BLEU points across 7 language pairs.We also show that our mined transliteration corpora provide better rule coverage and translation quality compared to the gold standard transliteration corpora.

Source: Conference of the European Chapter of the Association for Computational Linguistics

DOI: 10.3115/v1/e14-4029

Authors: Nadir Durrani, Hassan Sajjad, Hieu Hoang, Philipp Koehn

Institution: University of Edinburgh

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: European Commission

Awards: G3207356259, Bridges Across the Language Divide, G393177772, G5702163051