A Sequence to Sequence Learning for Chinese Grammatical Error Correction

被引:22
|
作者
Ren, Hongkai [1 ,2 ]
Yang, Liner [1 ,2 ]
Xun, Endong [1 ,2 ]
机构
[1] Beijing Adv Innovat Ctr Language Resources, Beijing, Peoples R China
[2] Beijing Language & Culture Univ, Sch Informat Sci, Beijing, Peoples R China
关键词
Grammatical Error Correction; Convolutional Sequence to Sequence Model; Neural machine translation;
D O I
10.1007/978-3-319-99501-4_36
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Grammatical Error Correction (GEC) is an important task in natural language processing. In this paper, we introduce our system on NLPCC 2018 Shared Task 2 Grammatical Error Correction. The task is to detect and correct grammatical errors that occurred in Chinese essays written by non-native speakers of Mandarin Chinese. Our system is mainly based on the convolutional sequence-to-sequence model. We regard GEC as a translation task from the language of "bad" Chinese to the language of "good" Chinese. We describe the building process of the model in details. On the test data of NLPCC 2018 Shared Task 2, our system achieves the best precision score, and the F-0.5 score is 29.02. Our final results ranked third among the participants.
引用
收藏
页码:401 / 410
页数:10
相关论文
共 50 条
  • [1] Chinese Grammatical Error Correction Based on Convolutional Sequence to Sequence Model
    Li, Si
    Zhao, Jianbo
    Shi, Guirong
    Tan, Yuanpeng
    Xu, Huifang
    Chen, Guang
    Lan, Haibo
    Lin, Zhiqing
    [J]. IEEE ACCESS, 2019, 7 : 72905 - 72913
  • [2] A Chinese Grammatical Error Correction Method Based on Iterative Training and Sequence Tagging
    Kuang, Hailan
    Wu, Kewen
    Ma, Xiaolin
    Liu, Xinhua
    [J]. APPLIED SCIENCES-BASEL, 2022, 12 (09):
  • [3] An Extended Sequence Tagging Vocabulary for Grammatical Error Correction
    Mesham, Stuart
    Bryant, Christopher
    Rei, Marek
    Yuan, Zheng
    [J]. 17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 1608 - 1619
  • [4] Sequence-to-Action: Grammatical Error Correction with Action Guided Sequence Generation
    Li, Jiquan
    Guo, Junliang
    Zhu, Yongxin
    Sheng, Xin
    Jiang, Deqiang
    Ren, Bo
    Xu, Linli
    [J]. THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 10974 - 10982
  • [5] Automatic Grammatical Error Correction for Sequence-to-sequence Text Generation: An Empirical Study
    Ge, Tao
    Zhang, Xingxing
    Wei, Furu
    Zhou, Ming
    [J]. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 6059 - 6064
  • [6] Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction
    Li, Piji
    Shi, Shuming
    [J]. 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (ACL-IJCNLP 2021), VOL 1, 2021, : 4973 - 4984
  • [7] Grammatical Error Correction as GAN-like Sequence Labeling
    Parnow, Kevin
    Li, Zuchao
    Zhao, Hai
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 3284 - 3290
  • [8] Multi-head sequence tagging model for Grammatical Error Correction
    Al-Sabahi, Kamal
    Yang, Kang
    Liu, Wangwang
    Jiang, Guanyu
    Li, Xian
    Yang, Ming
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 133
  • [9] Ensembling and Knowledge Distilling of Large Sequence Taggers for Grammatical Error Correction
    Tarnavskyi, Maksym
    Chernodub, Artem
    Omelianchuk, Kostiantyn
    [J]. PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 3842 - 3852
  • [10] A Question answering System with a sequence to sequence grammatical correction
    Bghiel, Afrae
    Ben Ahmed, Mohamed
    Boudhir, A. Anouar
    [J]. 3RD INTERNATIONAL CONFERENCE ON NETWORKING, INFORMATION SYSTEM & SECURITY (NISS'20), 2020,