A unified approach for effectively integrating source-side syntactic reordering rules into phrase-based translation.

Phrase-based translation models, with sequences of words (phrases) as translation units, achieve state-of-the-art translation performance. However, phrase reordering is a major challenge for this model. Recently, researchers have focused on utilizing syntax to improve phrase reordering. In adding sy...

Descripción completa

Detalles Bibliográficos
Publicado en:Language Resources & Evaluation Vol. 47; no. 2; pp. 449 - 475
Autores principales: Zhang, Jiajun, Zong, Chengqing
Formato: Artículo
Publicado: Springer Nature Jun2013
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=87846093&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 87846093
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        1574020X
        179V
      jtl: Language Resources & Evaluation
      issn: 1574020X
      maglogo: N
    pubinfo:
      dt: Jun2013
      vid: 47
      iid: 2
      pid: 237
      pub: Springer Nature
    artinfo:
      ui:
        87846093
        10.1007/s10579-013-9217-4
      ppf: 449
      ppct: 26
      formats:
        fmt:
          @attributes:
            type: P
            size: 1MB
      tig:
        atl: A unified approach for effectively integrating source-side syntactic reordering rules into phrase-based translation.
      aug:
        au:
          Zhang, Jiajun
          Zong, Chengqing
        affil: National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190 China
      su:
        Phrase structure grammar
        Syntax (Grammar)
        Translations
        Vocabulary
        Language & languages
        Algorithms
      sug:
        subj:
          Phrase structure grammar
          Syntax (Grammar)
          Translations
          Vocabulary
          Language & languages
          Algorithms
      keyword:
        Effective integration
        Handcrafted syntactic rules
        Phrase-based translation
        Probabilistic syntactic rules
      ab: Phrase-based translation models, with sequences of words (phrases) as translation units, achieve state-of-the-art translation performance. However, phrase reordering is a major challenge for this model. Recently, researchers have focused on utilizing syntax to improve phrase reordering. In adding syntactic knowledge into phrase reordering model, using handcrafted or probabilistic syntactic rules to reorder the source-language approximating the target-language word order has been successful in improving translation quality. However, it suffers from propagating the pre-ordering errors to the later translation step (e.g. decoding). In this paper, we propose a novel framework to uniformly represent the handcrafted and probabilistic syntactic rules and integrate them more effectively into phrase-based translation. In the translation phase, for a source sentence to be translated, handcrafted or probabilistic syntactic rules are first acquired from the source parse tree prior to translation, and then instead of reordering the source sentence directly, we input these rules into the decoder and design a new algorithm to apply these rules during decoding. In order to attach more importance to the syntactic rules and distinguish reordering between syntactic and non-syntactic unit reordering, we propose to design respectively a syntactic reordering model and a non-syntactic reordering model. The syntactic rules will guide phrase reordering in decoding within the syntactic reordering model. Extensive experiments on Chinese-to-English translation show that our approach, whether incorporating handcrafted or probabilistic syntactic rules, significantly outperforms the previous methods.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      custom: Language Resources & Evaluation is a copyright of Springer, 2013. All Rights Reserved.
      item: Language Resources & Evaluation
      holder: Springer Nature
      dt:
        @attributes:
          year: 2013
    holdings:
      @attributes:
        islocal: N