skip to main content
10.1145/3207677.3278045acmotherconferencesArticle/Chapter ViewAbstractPublication PagescsaeConference Proceedingsconference-collections
research-article

Machine Reading Comprehension Based on the Combination of BIDAF Model and Word Vectors

Published: 22 October 2018 Publication History

Abstract

For humans1, reading comprehension is the most basic ability to acquire knowledge. The reading capabilities of machines are considered to be the basic capabilities of next-generation search engines and artificial intelligence products. Machine Comprehension (MC) requires complex interactions between contextual paragraphs and questions to answer the questions raised for a given contextual paragraph. This paper proposes a method based on the combination of Bi-Directional Attention Flow (BIDAF) model and word vectors, the model uses a two-way attention flow mechanism to capture context and problem attention. The experimental evaluation found that the method has a significant improvement over the previous Match-LSTM network, thus verifying the effectiveness of the method.

References

[1]
Kadlec R, Schmid M, and Bajgar O, et al. 2016. Text Understanding with the Attention Sum Reader Network. 908--918.
[2]
Liu F, Hao W, Chen G, Jin D, and Song J. 2017. Attention of Bilinear Function Based Bi-LSTM Model for Machine Reading Comprehension. PLA University of Science and Technology. Computer Science, 44(S1), 92--96+122.
[3]
Rajpurkar, Pranav, et al. 2016. SQuAD: 100,000+ Questions for Machine Comprehension of Text. Stanford University. Conference on Empirical Methods in Natural Language Processing, 2383--2392.
[4]
Seo M, Kembhavi A, and Farhadi A, et al. 2016. Bidirectional Attention Flow for Machine Comprehension. University of Washington.
[5]
D'Informatique D E, Ese N, and Esent P, et al. 2001. Long Short-Term Memory in Recurrent Neural Networks. Epfl, 9(8), 1735--1780.
[6]
Wang S, and Jiang J. 2016. Machine Comprehension Using Match-LSTM and Answer Pointer. Singapore Management University.
[7]
He W, Liu K, and Liu J, et al. 2017. DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications. Baidu Inc.

Cited By

View all
  • (2022)A Survey on Machine Reading Comprehension SystemsNatural Language Engineering10.1017/S1351324921000395(1-50)Online publication date: 19-Jan-2022

Index Terms

  1. Machine Reading Comprehension Based on the Combination of BIDAF Model and Word Vectors

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    CSAE '18: Proceedings of the 2nd International Conference on Computer Science and Application Engineering
    October 2018
    1083 pages
    ISBN:9781450365123
    DOI:10.1145/3207677
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 22 October 2018

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Bi-Directional Attention Flow Model
    2. machine comprehension
    3. word vectors

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    CSAE '18

    Acceptance Rates

    CSAE '18 Paper Acceptance Rate 189 of 383 submissions, 49%;
    Overall Acceptance Rate 368 of 770 submissions, 48%

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • Downloads (Last 12 months)4
    • Downloads (Last 6 weeks)0
    Reflects downloads up to 20 Feb 2025

    Other Metrics

    Citations

    Cited By

    View all
    • (2022)A Survey on Machine Reading Comprehension SystemsNatural Language Engineering10.1017/S1351324921000395(1-50)Online publication date: 19-Jan-2022

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media