Efficient Beam Thresholding for Statistical Machine Translation

Human Language Technology Institute for Infocomm Research; Fusionopolis Way, #21-01, 138632, Connexis, Singapore

ABSTRACT Beam thresholding is a widely-used pruning approach in decoding algorithms of statistical machine translation. In this paper, we pro-pose two variations on the conventional beam thresholding, both of which speed up the de-coding without degrading BLEU score. The first variation is the dynamic beam threshold-ing, in which the beam threshold varies with the length of source sequences covered by hy-potheses. The second one incorporates a lan-guage model look-ahead probability into the beam thresholding so that the interaction be-tween a hypothesis and the contexts outside the hypothesis can be captured. Both thresh-olding methods achieve significant speed im-provements when used separately. By com-bining them together, we obtain a further speedup, which is comparable to that of the cube pruning approach (Chiang, 2007). Ex-periments also display that the dynamic beam thresholding can further improve the cube pruning.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we describe an efficient A* search algorithm for statistical machine translation. In contrary to beamsearch or greedy approaches it is possible to guarantee the avoidance of search errors with A*. We develop various sophisticated admissible and almost admissible heuristic functions. Especially our newly developped method to perform a multi-pass A* search with an iteratively improved heuristic function allows us to translate even long sentences.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We propose a novel reordering model for phrase-based statistical machine transla- tion (SMT) that uses a maximum entropy (MaxEnt) model to predicate reorderings of neighbor blocks (phrase pairs). The model provides content-dependent, hier- archical phrasal reordering with general- ization based on features automatically learned from a real-world bitext. We present an algorithm to extract all reorder- ing events of neighbor blocks from bilin- gual data. In our experiments on Chinese- to-English translation, this MaxEnt-based reordering model obtains significant im- provements in BLEU score on the NIST MT-05 and IWSLT-04 tasks.
    ACL 2006, 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, Sydney, Australia, 17-21 July 2006; 01/2006
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: We introduce a polynomial-time algorithm for statistical machine translation. This algorithm can be used in place of the expensive, slow best-first search strategies in current statistical translation architectures. The approach employs the stochastic bracketing transduction grammar (SBTG) model we recently introduced to replace earlier word alignment channel models, while retaining a bigram language model. The new algorithm in our experience yields major speed improvement with no significant loss of accuracy.
    34th Annual Meeting of the Association for Computational Linguistics, 24-27 June 1996, University of California, Santa Cruz, California, USA, Proceedings.; 01/1996

Full-text (2 Sources)

Available from
Jun 1, 2014