Asymmetric term alignment with selective contiguity constraints by multi-tape automata

  • 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.

Download full text files

Export metadata

Additional Services

Share in Twitter Search Google Scholar Statistics
Author:Mădălina Barbaiani, Nicola Cancedda, Chris Dance, Szilárd Fazekas, Tamás Gaál, Éric Gaussier
Document Type:Conference Proceeding
Year of Completion:2008
Publishing Institution:Universität Potsdam
Release Date:2008/12/11
Organizational units:Extern / Extern
Dewey Decimal Classification:4 Sprache / 40 Sprache / 400 Sprache
Collections:Universität Potsdam / Tagungsbände/Proceedings (nicht forlaufend) / Finite-state methods and natural language processing : 6th International Workshop, FSMNLP 2007 / II Regular Papers
Licence (German):License LogoKeine Nutzungslizenz vergeben - es gilt das deutsche Urheberrecht
Notes extern:
The complete edition of the proceedings "Finite-state methods and natural language processing : 6th International Workshop, FSMNLP 2007 ; Revised Papers" is available:
URN urn:nbn:de:kobv:517-opus-23812