Learning a translation model from word lattices

Oliver Adams, Graham Neubig, Trevor Cohn, Steven Bird

    Research output: Contribution to journalConference article

    Abstract

    Translation models have been used to improve automatic speech recognition when speech input is paired with a written translation, primarily for the task of computer-aided translation. Existing approaches require large amounts of parallel text for training the translation models, but for many language pairs this data is not available. We propose a model for learning lexical translation parameters directly from the word lattices for which a transcription is sought. The model is expressed through composition of each lattice with a weighted finite-state transducer representing the translation model, where inference is performed by sampling paths through the composed finitestate transducer. We show consistent word error rate reductions in two datasets, using between just 20 minutes and 4 hours of speech input, additionally outperforming a translation model trained on the 1-best path.

    Original languageEnglish
    Pages (from-to)2518-2522
    Number of pages5
    JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
    Volume08-12-September-2016
    DOIs
    Publication statusPublished - 1 Jan 2016
    Event17th Annual Conference of the International Speech Communication Association, INTERSPEECH 2016 - San Francisco, United States
    Duration: 8 Sep 201616 Sep 2016

    Fingerprint Dive into the research topics of 'Learning a translation model from word lattices'. Together they form a unique fingerprint.

  • Cite this