Probabilistic top-down parsing and language modeling

被引:129
|
作者
Roark, B [1 ]
机构
[1] Brown Univ, Dept Cognit & Linguist Sci, Providence, RI 02912 USA
关键词
All Open Access; Hybrid Gold; Green;
D O I
10.1162/089120101750300526
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper describes the functioning of a broad-coverage probabilistic top-down parser, and its application to the problem of language modeling for speech recognition. The paper first introduces key notions in language modeling and probabilistic pausing, and briefly reviews some previous approaches to using syntactic structure for language modeling. A lexicalized probabilistic top-down parser is then presented, which performs very well, in terms of both the accuracy of returned parses and the efficiency with which they are found, relative to the best broad-coverage statistical parsers. A new language model that utilizes probabilistic top-down parsing is then outlined, and empirical results show that it improves upon previous work in test corpus perplexity Interpolation with a trigram model yields an exceptional improvement relative to the improvement observed by other models, demonstrating the degree to which the information captured by our parsing model is orthogonal to that captured by a trigram model. A small recognition experiment also demonstrates the utility of the model.
引用
收藏
页码:249 / 276
页数:28
相关论文
共 50 条
  • [1] SQUIBS AND DISCUSSIONS - MEMOIZATION IN TOP-DOWN PARSING
    JOHNSON, M
    COMPUTATIONAL LINGUISTICS, 1995, 21 (03) : 405 - 417
  • [2] TOP-DOWN PARSING IN COCO-2
    DOBLER, H
    SIGPLAN NOTICES, 1991, 26 (03): : 79 - 87
  • [3] ATTRIBUTE-DIRECTED TOP-DOWN PARSING
    MULLER, K
    LECTURE NOTES IN COMPUTER SCIENCE, 1992, 641 : 37 - 43
  • [4] TOP-DOWN LANGUAGE ANALYZER
    SMITH, JW
    THARP, AL
    INTERNATIONAL JOURNAL OF MAN-MACHINE STUDIES, 1979, 11 (03): : 325 - 338
  • [5] Predictive Top-Down Parsing for Hyperedge Replacement Grammars
    Drewes, Frank
    Hoffmann, Berthold
    Minas, Mark
    GRAPH TRANSFORMATION (ICGT 2015), 2015, 9151 : 19 - 34
  • [6] Top-down Discourse Parsing via Sequence Labelling
    Koto, Fajri
    Lau, Jey Han
    Baldwin, Timothy
    16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), 2021, : 715 - 726
  • [7] HEMISPHERICITY AND TOP-DOWN PROCESSING OF LANGUAGE
    FAUST, M
    KRAVETZ, S
    BABKOFF, H
    BRAIN AND LANGUAGE, 1993, 44 (01) : 1 - 18
  • [8] Core Semantic First: A Top-down Approach for AMR Parsing
    Cai, Deng
    Lam, Wai
    2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 3799 - 3809
  • [9] Efficient Top-Down BTG Parsing for Machine Translation Preordering
    Nakagawa, Tetsuji
    PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1, 2015, : 208 - 218
  • [10] Top-down parsing with simultaneous evaluation of noncircular attribute grammars
    Noll, Thomas
    Vogler, Heiko
    Fundamenta Informaticae, 1994, 20 (04) : 285 - 332