Text Feature Extraction and Selection Based on Attention Mechanism

被引:0
|
作者
Ma, Longxuan [1 ]
Zhang, Lei [1 ]
机构
[1] Beijing Univ Posts & Telecommun, Beijing, Peoples R China
关键词
Feature extraction and selection; Machine learning; Question answering;
D O I
10.1007/978-3-030-16145-3_48
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Selecting features that represent a particular corpus is important to the success of many machine learning and text mining applications. However, the previous attention-based work only focused on feature augmentation in the lexical level, lacking the exploration of feature enhancement in the sentence level. In this paper, we exploit a novel feature extraction and selection model for information retrieval, denoted by Dynamic Feature Generation Network (DFGN). In sentence dimension, features are firstly extracted by a variety of different attention mechanisms, then dynamically filtered by thresholds automatically learned. Different kinds of characteristics are distilled according to specific tasks, enhancing the practicability and robustness of the model. DFGN relies solely on the text itself, requires no external feature engineering. Our approach outperforms previous work on multiple well-known answer selection datasets. Through the analysis of the experiments, we prove that DFGN provides excellent retrieval and interpretative abilities.
引用
收藏
页码:615 / 627
页数:13
相关论文
共 50 条
  • [1] A Review on Feature Selection and Feature Extraction for Text Classification
    Shah, Foram P.
    Patel, Vibha
    [J]. PROCEEDINGS OF THE 2016 IEEE INTERNATIONAL CONFERENCE ON WIRELESS COMMUNICATIONS, SIGNAL PROCESSING AND NETWORKING (WISPNET), 2016, : 2264 - 2268
  • [2] AFS: An Attention-Based Mechanism for Supervised Feature Selection
    Gui, Ning
    Ge, Danni
    Hu, Ziyin
    [J]. THIRTY-THIRD AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FIRST INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE / NINTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2019, : 3705 - 3713
  • [3] Feature Selection for Event Extraction in Biomedical Text
    Majumder, Amit
    Hasanuzzaman, Mohammed
    Ekbal, Asif
    [J]. 2015 EIGHTH INTERNATIONAL CONFERENCE ON ADVANCES IN PATTERN RECOGNITION (ICAPR), 2015, : 241 - +
  • [4] Composite Feature Extraction and Selection for Text Classification
    Wan, Chuan
    Wang, Yuling
    Liu, Yaoze
    Ji, Jinchao
    Feng, Guozhong
    [J]. IEEE ACCESS, 2019, 7 : 35208 - 35219
  • [5] A Feature Selection Methods Based on Concept Extraction and SOM Text Clustering Analysis
    Wang, Lin
    Jiang, Minghu
    Liao, Shasha
    Lu, Yinghua
    [J]. INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2006, 6 (1A): : 20 - 28
  • [6] A NEW FEATURE SELECTION METHOD BASED ON CONCEPT EXTRACTION IN AUTOMATIC CHINESE TEXT CLASSIFICATION
    Liao, Shasha
    Jiang, Minghu
    [J]. NEW MATHEMATICS AND NATURAL COMPUTATION, 2007, 3 (03) : 331 - 347
  • [7] Feature Extraction based Text Classification: A review
    Shaker, Saif Safaa
    Alhajim, Dhafer
    Al-Khazaali, Ahmed Ali Talib
    Hussein, Hussein Aqeel
    Athab, Ali F.
    [J]. JOURNAL OF ALGEBRAIC STATISTICS, 2022, 13 (01) : 646 - 653
  • [8] A Multi-Scale Natural Scene Text Detection Method Based on Attention Feature Extraction and Cascade Feature Fusion
    Li, Nianfeng
    Wang, Zhenyan
    Huang, Yongyuan
    Tian, Jia
    Li, Xinyuan
    Xiao, Zhiguo
    [J]. SENSORS, 2024, 24 (12)
  • [9] The feature extraction of text mining based on Web
    Liu, LZ
    Chen, JJ
    Song, HT
    [J]. ICEMI'2003: PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON ELECTRONIC MEASUREMENT & INSTRUMENTS, VOLS 1-3, 2003, : 547 - 550
  • [10] Feature Extraction in Text Clustering Based on Theme
    Shi, Nianyun
    Jing, Kong
    Xu, Jiuyun
    Duan, Yongxiang
    Li, Chunhua
    [J]. 2008 INTERNATIONAL SYMPOSIUM ON INTELLIGENT INFORMATION TECHNOLOGY APPLICATION WORKSHOP: IITA 2008 WORKSHOPS, PROCEEDINGS, 2008, : 632 - +