Using WFSTs for Efficient EM Learning of Probabilistic CFGs and Their Extensions

DOI
  • Kameya Yoshitaka
    Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology
  • Mori Takashi
    Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology
  • Sato Taisuke
    Department of Computer Science, Graduate School of Information Science and Engineering, Tokyo Institute of Technology

抄録

Probabilistic context-free grammars (PCFGs) are a widely known class of probabilistic language models. The Inside-Outside (I-O) algorithm is well known as an efficient EM algorithm tailored for PCFGs. Although the algorithm requires inexpensive linguistic resources, there remains a problem in its efficiency. This paper presents an efficient method for training PCFG parameters in which the parser is separated from the EM algorithm, assuming that the underlying CFG is given. A new EM algorithm exploits the compactness of well-formed substring tables (WFSTs) generated by the parser. Our proposal is general in that the input grammar need not take Chomsky normal form (CNF) while it is equivalent to the I-O algorithm in the CNF case. In addition, we propose a polynomial-time EM algorithm for CFGs with context-sensitive probabilities, and report experimental results with the ATR dialogue corpus and a hand-crafted Japanese grammar.

収録刊行物

詳細情報 詳細情報について

  • CRID
    1390001205265691520
  • NII論文ID
    130004705287
  • DOI
    10.11185/imt.9.517
  • ISSN
    18810896
  • 本文言語コード
    en
  • データソース種別
    • JaLC
    • CiNii Articles
  • 抄録ライセンスフラグ
    使用不可

問題の指摘

ページトップへ