Answering questions with an n-gram based passage retrieval engine

被引：0
|
作者：
Davide Buscaldi
Paolo Rosso
José Manuel Gómez-Soriano
Emilio Sanchis
机构：
[1] Universidad Politécnica de Valencia,ELiRF Research Group
[2] Universidad de Alicante, Departamento de Sistemas Informáticos y Computación
来源：
Journal of Intelligent Information Systems | 2010年 / 34卷
关键词：
Question answering; Information retrieval and extraction; Passage retrieval;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
In this paper, we present a Question Answering system based on redundancy and a Passage Retrieval method that is specifically oriented to Question Answering. We suppose that in a large enough document collection the answer to a given question may appear in several different forms. Therefore, it is possible to find one or more sentences that contain the answer and that also include tokens from the original question. The Passage Retrieval engine is almost language-independent since it is based on n-gram structures. Question classification and answer extraction modules are based on shallow patterns.
引用
收藏
页码：113 / 134
页数：21
相关论文
共 50 条
  • [1] Answering questions with an n-gram based passage retrieval engine
    Buscaldi, Davide
    Rosso, Paolo
    Manuel Gomez-Soriano, Jose
    Sanchis, Emilio
    [J]. JOURNAL OF INTELLIGENT INFORMATION SYSTEMS, 2010, 34 (02) : 113 - 134
  • [2] N-gram vs. keyword-based passage retrieval for question answering
    Buscaldi, Davide
    Gomez, Jose Manuel
    Rosso, Paolo
    Sanchis, Emilio
    [J]. EVALUATION OF MULTILINGUAL AND MULTI-MODAL INFORMATION RETRIEVAL, 2007, 4730 : 377 - +
  • [3] Character-Based N-gram Model for Uyghur Text Retrieval
    Tohti, Turdi
    Xu, Lirui
    Huang, Jimmy
    Musajan, Winira
    Hamdulla, Askar
    [J]. BIOMETRIC RECOGNITION, CCBR 2018, 2018, 10996 : 678 - 688
  • [4] Revisiting N-Gram Based Models for Retrieval in Degraded Large Collections
    Parapar, Javier
    Freire, Ana
    Barreiro, Alvaro
    [J]. ADVANCES IN INFORMATION RETRIEVAL, PROCEEDINGS, 2009, 5478 : 680 - 684
  • [5] An efficient document retrieval method using n-gram indexing
    Ogawa, Yasushi
    Matsuda, Toru
    [J]. Systems and Computers in Japan, 2002, 33 (02) : 54 - 63
  • [6] Character N-Gram Tokenization for European Language Text Retrieval
    Paul McNamee
    James Mayfield
    [J]. Information Retrieval, 2004, 7 : 73 - 97
  • [7] N-gram and local context analysis for Persian text retrieval
    Aleahmad, Abolfazl
    Hakimian, Parsia
    Mahdikhani, Farzad
    Oroumchian, Farhad
    [J]. 2007 9TH INTERNATIONAL SYMPOSIUM ON SIGNAL PROCESSING AND ITS APPLICATIONS, VOLS 1-3, 2007, : 284 - 287
  • [8] Character N-gram tokenization for European language text retrieval
    McNamee, P
    Mayfield, J
    [J]. INFORMATION RETRIEVAL, 2004, 7 (1-2): : 73 - 97
  • [9] Evaluation of N-Gram Conflation Approaches for Arabic Text Retrieval
    Ahmed, Farag
    Nuernberger, Andreas
    [J]. JOURNAL OF THE AMERICAN SOCIETY FOR INFORMATION SCIENCE AND TECHNOLOGY, 2009, 60 (07): : 1448 - 1465
  • [10] Techniques for gigabyte-scale n-gram based information retrieval on personal computers
    Miller, E
    Shen, D
    Liu, JL
    Nicholas, C
    Chen, T
    [J]. INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-V, PROCEEDINGS, 1999, : 1410 - 1416
12345