This article describes a HMM-based word-alignment method that can selectively enforce a contiguity constraint. This method has a direct application in the extraction of a bilingual terminological lexicon from a parallel corpus, but can also be used as a preliminary step for the extraction of phrase pairs in a Phrase-Based Statistical Machine Translation system. Contiguous source words composing terms are aligned to contiguous target language words. The HMM is transformed into a Weighted Finite State Transducer (WFST) and contiguity constraints are enforced by specific multi-tape WFSTs. The proposed method is especially suited when basic linguistic resources (morphological analyzer, part-of-speech taggers and term extractors) are available for the source language only.
Identifer | oai:union.ndltd.org:Potsdam/oai:kobv.de-opus-ubp:2711 |
Date | January 2008 |
Creators | Barbaiani, Mădălina, Cancedda, Nicola, Dance, Chris, Fazekas, Szilárd, Gaál, Tamás, Gaussier, Éric |
Publisher | Universität Potsdam, Extern. Extern |
Source Sets | Potsdam University |
Language | English |
Detected Language | English |
Type | InProceedings |
Format | application/pdf |
Rights | http://opus.kobv.de/ubp/doku/urheberrecht.php |
Page generated in 0.002 seconds