Using Parsed Corpora for Estimating Stochastic Inversion Transduction Grammars

被引:0
|
作者
Sanchis-Trilles, German [1 ]
Andreu Sanchez, Joan [1 ]
机构
[1] Univ Politecn Informat, Inst Tecnol Informat, Valencia 46022, Spain
关键词
D O I
暂无
中图分类号
H0 [语言学];
学科分类号
030303 ; 0501 ; 050102 ;
摘要
An important problem when using Stochastic Inversion Transduction Grammars is their computational cost. More specifically, when dealing with corpora such as Europarl only one iteration of the estimation algorithm becomes prohibitive. In this work, we apply a reduction of the cost by taking profit of the bracketing information in parsed corpora and show machine translation results obtained with a bracketed Europarl corpus, yielding interresting improvements when increasing the number of non-terminal symbols.
引用
收藏
页码:1825 / 1827
页数:3
相关论文
共 50 条
  • [2] Stochastic Inversion Transduction Grammars and Bilingual Parsing of Parallel Corpora
    Department of Computer Science, University of Science and Technology, Clear Water Bay, Hong Kong, Hong Kong
    Comput. Linguist., 3 (377-403):
  • [3] Treebanks: Building and using parsed corpora
    Resnik, Philip
    LANGUAGE, 2007, 83 (04) : 876 - 880
  • [4] Textual entailment recognition using inversion transduction grammars
    Wu, Dekai
    MACHINE LEARNING CHALLENGES: EVALUATING PREDICTIVE UNCERTAINTY VISUAL OBJECT CLASSIFICATION AND RECOGNIZING TEXTUAL ENTAILMENT, 2006, 3944 : 299 - 308
  • [5] Using Dominance Chains to Detect Annotation Variants in Parsed Corpora
    Faria, Pablo
    2014 IEEE 10TH INTERNATIONAL CONFERENCE ON ESCIENCE WORKSHOPS (ESCIENCE 2014), VOL 2, 2014, : 25 - 32
  • [6] Using parsed and annotated corpora to analyze parliamentarians' talk in Finland
    Andrushchenko, Mykola
    Sandberg, Kirsi
    Turunen, Risto
    Marjanen, Jani
    Hatavara, Mari
    Kurunmaki, Jussi
    Nummenmaa, Timo
    Hyvarinen, Matti
    Teras, Kari
    Peltonen, Jaakko
    Nummenmaa, Jyrki
    JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY, 2022, 73 (02) : 288 - 302
  • [7] Syntax Augmented Inversion Transduction Grammars for Machine Translation
    Gasco Mora, Guillem
    Sanchez Peiro, Joan Andreu
    COMPUTATIONAL LINGUISTICS AND INTELLIGENT TEXT PROCESSING, 2010, 6008 : 427 - 437
  • [8] Extraction of multiword expressions from parsed corpora using context features
    Weller, Marion
    Heid, Ulrich
    LREC 2010 - SEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2010,
  • [9] Extraction of German multiword expressions from parsed corpora using context features
    Weller, Marion
    Heid, Ulrich
    LREC 2010 - SEVENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2010, : 3195 - 3201
  • [10] Using very large parsed corpora and judgment data to classify verb reflexivity
    Smits, Erik-Jan
    Hendriks, Petra
    Spenader, Jennifer
    ANAPHORA: ANALYSIS, ALGORITHMS AND APPLICATIONS, 2007, 4410 : 77 - +