cdec: A Decoder, Alignment, and Learning Framework for Finite-State and Context-Free Translation Models

Chris Dyer, Adam Lopez, Juri Ganitkevitch, Jonathan Weese, Ferhan Ture, Phil Blunsom, Hendra Setiawan, Vladimir Eidelman, Philip Resnik

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present cdec, an open source framework for decoding, aligning with, and training a number of statistical machine translation models, including word-based models, phrase-based models, and models based on synchronous context-free grammars. Using a single unified internal representation for translation forests, the decoder strictly separates model-specific translation logic from general rescoring, pruning, and inference algorithms. From this unified representation, the decoder can extract not only the 1- or k-best translations, but also alignments to a reference, or the quantities necessary to drive discriminative training using gradient-based or gradient-free optimization techniques. Its efficient C++ implementation means that memory use and runtime performance are significantly better than comparable decoders.
Original languageEnglish
Title of host publicationProceedings of the ACL 2010 System Demonstrations
Place of PublicationUppsala, Sweden
PublisherAssociation for Computational Linguistics
Pages7-12
Number of pages6
Publication statusPublished - 1 Jul 2010

Fingerprint

Dive into the research topics of 'cdec: A Decoder, Alignment, and Learning Framework for Finite-State and Context-Free Translation Models'. Together they form a unique fingerprint.

Cite this