Similarity-Based Models of Word Cooccurrence Probabilities

被引：0
|
作者：
Ido Dagan
Lillian Lee
Fernando C. N. Pereira
机构：
[1] Bar Ilan University,Dept. of Mathematics and Computer Science
[2] Cornell University,Department of Computer Science
[3] AT&T Labs—Research,undefined
来源：
Machine Learning | 1999年 / 34卷
关键词：
Statistical language modeling; sense disambiguation;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In many applications of natural language processing (NLP) it is necessary to determine the likelihood of a given word combination. For example, a speech recognizer may need to determine which of the two word combinations “eat a peach” and ”eat a beach” is more likely. Statistical NLP methods determine the likelihood of a word combination from its frequency in a training corpus. However, the nature of language is such that many word combinations are infrequent and do not occur in any given corpus. In this work we propose a method for estimating the probability of such previously unseen word combinations using available information on “most similar” words.
引用
收藏
页码：43 / 69
页数：26
相关论文
共 50 条
  • [1] Similarity-based models of word cooccurrence probabilities
    Dagan, I
    Lee, L
    Pereira, FCN
    [J]. MACHINE LEARNING, 1999, 34 (1-3) : 43 - 69
  • [2] Similarity-based word sense disambiguation
    Karov, Y
    Edelman, S
    [J]. COMPUTATIONAL LINGUISTICS, 1998, 24 (01) : 41 - 59
  • [3] Ensembles of similarity-based models
    Duch, W
    Grudzinski, K
    [J]. INTELLIGENT INFORMATION SYSTEMS 2001, 2001, : 75 - 85
  • [4] Similarity-based methods for word sense disambiguation
    Dagan, I
    Lee, L
    Pereira, F
    [J]. 35TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 8TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE, 1997, : 56 - 63
  • [5] Generative models for similarity-based classification
    Cazzanti, Luca
    Gupta, Maya R.
    Koppal, Anjah J.
    [J]. PATTERN RECOGNITION, 2008, 41 (07) : 2289 - 2297
  • [6] Similarity-based heterogeneous neuron models
    Muñoz, LAB
    [J]. ECAI 2000: 14TH EUROPEAN CONFERENCE ON ARTIFICIAL INTELLIGENCE, PROCEEDINGS, 2000, 54 : 271 - 275
  • [7] Similarity-based models of human visual recognition
    Unzicker, A
    Jüttner, M
    Rentschler, I
    [J]. VISION RESEARCH, 1998, 38 (15-16) : 2289 - 2305
  • [8] EXTENDING SIMILARITY-BASED EPISTEMOLOGY OF MODALITY WITH MODELS
    Wirling, Ylwa Sjoelin
    [J]. ERGO-AN OPEN ACCESS JOURNAL OF PHILOSOPHY, 2021, 8 : 570 - 594
  • [9] Enhancing the Context Representation in Similarity-based Word Sense Disambiguation
    Wang, Ming
    Zhang, Jianzhang
    Wang, Yinglin
    [J]. 2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 8965 - 8973
  • [10] Fuzzy similarity-based models in case-based reasoning
    Esteva, F
    Garcia-Calvés, P
    Godo, L
    [J]. PROCEEDINGS OF THE 2002 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOL 1 & 2, 2002, : 1348 - 1353
12345