Improving Word Alignment Through Morphological Analysis

被引:0
|
作者
Vuong Van Bui [1 ]
Thanh Trung Tran [1 ]
Nhat Bich Thi Nguyen [1 ]
Tai Dinh Pham [1 ]
Anh Ngoc Le [1 ]
Cuong Anh Le [1 ]
机构
[1] Univ Engn & Technol, Vietnam Natl Univ, Dept Comp Sci, Hanoi, Vietnam
来源
INTEGRATED UNCERTAINTY IN KNOWLEDGE MODELLING AND DECISION MAKING, IUKM 2015 | 2015年 / 9376卷
关键词
Machine translation; Word alignment; IBM models; Morphological analysis;
D O I
10.1007/978-3-319-25135-6_30
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Word alignment plays a critical role in statistical machine translation systems. The famous word alignment system, IBM models series, currently operates on only surface forms of words regardless of their linguistic features. This deficiency usually leads to many data sparseness problems. Therefore, we present an extension that enables the integration of morphological analysis into the traditional IBM models. Experiments on English-Vietnamese tasks show that the new model produces better results not only in word alignment but also in final translation performance.
引用
收藏
页码:315 / 325
页数:11
相关论文
共 50 条
  • [11] Guidelines for word alignment evaluation and manual alignment
    Lambert, Patrik
    De Gispert, Adria
    Banchs, Rafael
    Marino, Jose B.
    LANGUAGE RESOURCES AND EVALUATION, 2005, 39 (04) : 267 - 285
  • [12] Guidelines for Word Alignment Evaluation and Manual Alignment
    Patrik Lambert
    Adrià De Gispert
    Rafael Banchs
    José B. Mariño
    Language Resources and Evaluation, 2005, 39 : 267 - 285
  • [13] Word Alignment for English-Turkish Language Pair
    Cakmak, M. Talha
    Acar, Suleyman
    Eryigit, Gulsen
    LREC 2012 - EIGHTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2012, : 2177 - 2180
  • [14] Improving the Quality of Word Alignment By Integrating Pearson's Chi-square Test Information
    Cuong Hoang
    Cuong Anh Le
    Son Bao Pham
    2012 INTERNATIONAL CONFERENCE ON ASIAN LANGUAGE PROCESSING (IALP 2012), 2012, : 121 - 124
  • [15] Effective Integration of Automatic Word Spacing and Morphological Analysis in Korean
    Kim, Hongjin
    Kim, Harksoo
    2020 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP 2020), 2020, : 275 - 278
  • [16] UPDATING FIELD ASSOCIATION WORD DICTIONARY USING WORD ATTRIBUTES, MORPHOLOGICAL ANALYSIS, AND COMPOUND WORDS
    Atlam, El-Sayed
    INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2014, 10 (06): : 2097 - 2111
  • [17] Improving the Polarity of Text through word2vec Embedding for Primary Classical Arabic Sentiment Analysis
    Aoumeur, Nour Elhouda
    Li, Zhiyong
    Alshari, Eissa M. M.
    NEURAL PROCESSING LETTERS, 2023, 55 (03) : 2249 - 2264
  • [18] Using Kazakh Morphology Information to Improve Word Alignment for SMT
    Kartbayev, Amandyk
    PROCEEDINGS OF THE SECOND INTERNATIONAL AFRO-EUROPEAN CONFERENCE FOR INDUSTRIAL ADVANCEMENT (AECIA 2015), 2016, 427 : 351 - 359
  • [19] Lexicalized Syntactic Reordering Framework for Word Alignment and Machine Translation
    Huang, Chung-chi
    Chen, Wei-teh
    Chang, Jason S.
    COMPUTER PROCESSING OF ORIENTAL LANGUAGES: LANGUAGE TECHNOLOGY FOR THE KNOWLEDGE-BASED ECONOMY, 2009, 5459 : 103 - 111
  • [20] Multi-task Learning for Word Alignment and Dependency Parsing
    Liu, Shujie
    ARTIFICIAL INTELLIGENCE AND COMPUTATIONAL INTELLIGENCE, PT III, 2011, 7004 : 151 - 158