An unsupervised approach to prepositional phrase attachment using contextually similar words

被引：0
|
作者：
Pantel, P [1 ]
Lin, DK [1 ]
机构：
[1] Univ Alberta, Dept Comp Sci, Edmonton, AB T6G 2H1, Canada
来源：
38TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE | 2000年
关键词：
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Prepositional phrase attachment is a common source of ambiguity in natural language processing. We present an unsupervised corpus-based approach to prepositional phrase attachment that achieves similar performance to supervised methods. Unlike previous unsupervised approaches in which training data is obtained by heuristic extraction of unambiguous examples from a corpus, we use an iterative process to extract training data from an automatically parsed corpus. Attachment decisions are made using a linear combination of features and low frequency events are approximated using contextually similar words.
引用
收藏
页码：101 / 108
页数：8
相关论文
共 50 条
  • [31] Handling OOV Words in NMT Using Unsupervised Bilingual Embedding
    Haddad, Hesam
    Fadaei, Hakimeh
    Faili, Heshaam
    2018 9TH INTERNATIONAL SYMPOSIUM ON TELECOMMUNICATIONS (IST), 2018, : 569 - 574
  • [32] Unsupervised Confidence Calibration Using Examples of Recognized Words and Their Contexts
    Asami, Taichi
    Kobashikawa, Satoshi
    Masataki, Hirokazu
    Yoshioka, Osamu
    Takahashi, Satoshi
    14TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2013), VOLS 1-5, 2013, : 2216 - 2220
  • [33] Adding New Words into a Language Model using Parameters of Known Words with Similar Behavior
    Orosanu, Luiza
    Jouvet, Denis
    1ST INTERNATIONAL CONFERENCE ON NATURAL LANGUAGE AND SPEECH PROCESSING, 2018, 128 : 18 - 24
  • [34] Finding similar RSS news articles using correlation-based phrase matching
    Pera, Maria Soledad
    Ng, Yiu-Kai
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, 2007, 4798 : 336 - +
  • [35] An Unsupervised Approach for Traffic Sign Recognition Based on Bag-of-Visual-Words
    Supriyanto, Catur
    Luthfiarta, Ardytha
    Zeniarja, Junta
    PROCEEDINGS OF 2016 8TH INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY AND ELECTRICAL ENGINEERING (ICITEE), 2016,
  • [36] Visual content representation using semantically similar visual words
    Kesorn, Kraisak
    Chimlek, Sutasinee
    Poslad, Stefan
    Piamsa-nga, Punpiti
    EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (09) : 11472 - 11481
  • [37] An unsupervised method for ranking translation words using a bilingual dictionary and WordNet
    Kim, Kweon Yang
    Park, Se Young
    Hong, Dong Kwon
    ADVANCES IN APPLIED ARTICIAL INTELLIGENCE, PROCEEDINGS, 2006, 4031 : 879 - 888
  • [38] Unsupervised natural language disambiguation using non-ambiguous words
    Mihalcea, R
    RECENT ADVANCES IN NATURAL LANGUAGE PROCESSING III, 2004, 260 : 387 - 396
  • [39] Unsupervised segmentation of words using prior distributions of morph length and frequency
    Creutz, M
    41ST ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, 2003, : 280 - 287
  • [40] A flexible unsupervised PP-attachment method using semantic information
    Deptt. of Computer Sc. and Engg, Indian Institute of Technology Bombay, Mumbai, 400076, India
    IJCAI Int. Joint Conf. Artif. Intell., (1677-1682):
12345