Work

Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora

Year: 2007

Type: conference-paper

Abstract: Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation es-timates and low coverage over source and target phrases. This paper presents a method which alleviates this problem by exploit-ing multiple translations of the same source phrase. Central to our approach is triangula-tion, the process of translating from a source to a target language via an intermediate third language. This allows the use of a much wider range of parallel corpora for train-ing, and can be combined with a standard phrase-table using conventional smoothing methods. Experimental results demonstrate BLEU improvements for triangulated mod-els over a standard phrase-based system. 1

Source: Edinburgh Research Explorer (University of Edinburgh)

Authors: Trevor Cohn, Mirella Lapata

Institution: University of Edinburgh

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funder: Engineering and Physical Sciences Research Council

Award: Application-based Text-to-Text Generation

OpenAlex ID: W2170204377