Learning the Morphological and Syntactic Grammars for Named Entity Recognition

被引:5
|
作者
Sun, Mengtao [1 ]
Yang, Qiang [2 ]
Wang, Hao [3 ]
Pasquine, Mark [4 ]
Hameed, Ibrahim A. [1 ]
机构
[1] Norwegian Univ Sci & Technol, Dept ICT & Nat Sci, N-6009 Alesund, Norway
[2] China Telecom Middle East FZ LLC, Dubai 500482, U Arab Emirates
[3] Norwegian Univ Sci & Technol, Dept Comp Sci, N-2815 Gjovik, Norway
[4] Norwegian Univ Sci & Technol, Dept Int Business, N-6009 Alesund, Norway
关键词
named entity recognition; morphology; syntax; language processing; deep learning;
D O I
10.3390/info13020049
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
In some languages, Named Entity Recognition (NER) is severely hindered by complex linguistic structures, such as inflection, that will confuse the data-driven models when perceiving the word's actual meaning. This work tries to alleviate these problems by introducing a novel neural network based on morphological and syntactic grammars. The experiments were performed in four Nordic languages, which have many grammar rules. The model was named the NorG network (Nor: Nordic Languages, G: Grammar). In addition to learning from the text content, the NorG network also learns from the word writing form, the POS tag, and dependency. The proposed neural network consists of a bidirectional Long Short-Term Memory (Bi-LSTM) layer to capture word-level grammars, while a bidirectional Graph Attention (Bi-GAT) layer is used to capture sentence-level grammars. Experimental results from four languages show that the grammar-assisted network significantly improves the results against baselines. We also investigate how the NorG network works on each grammar component by some exploratory experiments.
引用
收藏
页数:16
相关论文
共 50 条
  • [1] Named entity recognition for Arabic using syntactic grammars
    Mesfar, Slim
    [J]. Natural Language Processing and Information Systems, Proceedings, 2007, 4592 : 305 - 316
  • [2] A system for named entity recognition based on local grammars
    Krstev, Cvetana
    Obradovic, Ivan
    Utvic, Milos
    Vitas, Dusko
    [J]. JOURNAL OF LOGIC AND COMPUTATION, 2014, 24 (02) : 473 - 489
  • [3] Improving biomedical named entity recognition with syntactic information
    Yuanhe Tian
    Wang Shen
    Yan Song
    Fei Xia
    Min He
    Kenli Li
    [J]. BMC Bioinformatics, 21
  • [4] Improving biomedical named entity recognition with syntactic information
    Tian, Yuanhe
    Shen, Wang
    Song, Yan
    Xia, Fei
    He, Min
    Li, Kenli
    [J]. BMC BIOINFORMATICS, 2020, 21 (01)
  • [5] Named Entity Recognition of Protein Complex Incorporating Syntactic Information
    Ruan, Junsong
    Zhang, Hailin
    Zhu, Hai
    Ding, Ruoyao
    [J]. 2022 INTERNATIONAL CONFERENCE ON ASIAN LANGUAGE PROCESSING (IALP 2022), 2022, : 241 - 246
  • [6] Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information
    Nie, Yuyang
    Tian, Yuanhe
    Song, Yan
    Ao, Xiang
    Wan, Xiang
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 4231 - 4245
  • [7] Chinese Named Entity Recognition Fusing Lexical and Syntactic Information
    Zhang, Min
    Li, Bicheng
    Liu, Qilong
    Wu, Jing
    [J]. 6TH INTERNATIONAL CONFERENCE ON INNOVATION IN ARTIFICIAL INTELLIGENCE, ICIAI2022, 2022, : 69 - 77
  • [8] Continual Learning for Named Entity Recognition
    Monaikul, Natawut
    Castellucci, Giuseppe
    Filice, Simone
    Rokhlenko, Oleg
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 13570 - 13577
  • [9] Ensemble Learning for Named Entity Recognition
    Speck, Rene
    Ngomo, Axel-Cyrille Ngonga
    [J]. SEMANTIC WEB - ISWC 2014, PT I, 2014, 8796 : 519 - 534
  • [10] Automatic rule learning exploiting morphological features for named entity recognition in Turkish
    Tatar, Serhan
    Cicekli, Ilyas
    [J]. JOURNAL OF INFORMATION SCIENCE, 2011, 37 (02) : 137 - 151