Structured Training for Neural Network Transition-Based Parsing

被引：79
|
作者：
Weiss, David [1 ]
Alberti, Chris [1 ]
Collins, Michael [1 ]
Petrov, Slav [1 ]
机构：
[1] Google Inc, New York, NY 10011 USA
来源：
PROCEEDINGS OF THE 53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 | 2015年
关键词：
D O I：
10.3115/v1/p15-1032
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
We present structured perceptron training for neural network transition-based dependency parsing. We learn the neural network representation using a gold corpus augmented by a large number of automatically parsed sentences. Given this fixed network representation, we learn a final layer using the structured perceptron with beam-search decoding. On the Penn Treebank, our parser reaches 94.26% unlabeled and 92.41% labeled attachment accuracy, which to our knowledge is the best accuracy on Stanford Dependencies to date. We also provide in-depth ablative analysis to determine which aspects of our model provide the largest gains in accuracy.
引用
收藏
页码：323 / 333
页数：11
相关论文
共 50 条
  • [31] Improving Feature-Rich Transition-Based Constituent Parsing Using Recurrent Neural Networks
    Ma, Chunpeng
    Tamura, Akihiro
    Liu, Lemao
    Zhao, Tiejun
    Sumita, Eiichiro
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2017, E100D (09) : 2205 - 2214
  • [32] Exploring Automatic Feature Selection for Transition-Based Dependency Parsing
    Ballesteros, Miguel
    PROCESAMIENTO DEL LENGUAJE NATURAL, 2013, (51): : 119 - 126
  • [33] Global Transition-based Non-projective Dependency Parsing
    Gomez-Rodriguez, Carlos
    Shi, Tianze
    Lee, Lillian
    PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1, 2018, : 2664 - 2675
  • [34] Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning
    Naseem, Tahira
    Shah, Abhishek
    Wan, Hui
    Florian, Radu
    Roukos, Salim
    Ballesteros, Miguel
    57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 4586 - 4592
  • [35] A Transition-based Approach for AMR Parsing using LSTM Networks
    Cimpian, Silviana
    Lazar, Andreea
    Macicasan, Florin
    Lemnaru, Camelia
    2017 13TH IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTER COMMUNICATION AND PROCESSING (ICCP), 2017, : 103 - 110
  • [36] Graph-to-Graph Transformer for Transition-based Dependency Parsing
    Mohammadshahi, Alireza
    Henderson, James
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020,
  • [37] Better Transition-Based AMR Parsing with a Refined Search Space
    Guo, Zhijiang
    Lu, Wei
    2018 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2018), 2018, : 1712 - 1722
  • [38] Generalized Transition-based Dependency Parsing via Control Parameters
    Bohnet, Bernd
    McDonald, Ryan
    Pitler, Emily
    Ma, Ji
    PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2016, : 150 - 160
  • [39] Transition-based Dependency DAG Parsing Using Dynamic Oracles
    Tokgoz, Alper
    Eryigit, Gulsen
    53RD ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 7TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING: PROCEEDINGS OF THE STUDENT RESEARCH WORKSHOP (ACL-IJCNLP 2015), 2015, : 22 - 27
  • [40] Transition-Based Neural Word Segmentation
    Zhang, Meishan
    Zhang, Yue
    Fu, Guohong
    PROCEEDINGS OF THE 54TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1, 2016, : 421 - 431
12345