Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

被引：0
|
作者：
Naseem, Tahira [1 ]
Shah, Abhishek [2 ]
Wan, Hui [1 ]
Florian, Radu [1 ]
Roukos, Salim [1 ]
Ballesteros, Miguel [1 ]
机构：
[1] IBM Res, Yorktown Hts, NY 10598 USA
[2] IBM Watson, New York, NY USA
来源：
57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019) | 2019年
关键词：
ALGORITHMS;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs. In addition, we also combined several AMR-to-text alignments with an attention mechanism and we supplemented the parser with pre-processed concept identification, named entities and contextualized embeddings. We achieve a highly competitive performance that is comparable to the best published results. We show an in-depth study ablating each of the new components of the parser.
引用
收藏
页码：4586 / 4592
页数：7
相关论文
共 50 条
  • [21] Undirected Dependency Structures for Transition-Based Parsing
    Gomez-Rodriguez, Carlos
    Fernandez-Gonzalez, Daniel
    PROCESAMIENTO DEL LENGUAJE NATURAL, 2012, (48): : 43 - 50
  • [22] Identifying Concepts and Relations in a Transition-Based AMR Parser
    Ieremias, Viorel
    Pop, Roxana
    Macicasan, Florin
    2019 IEEE 15TH INTERNATIONAL CONFERENCE ON INTELLIGENT COMPUTER COMMUNICATION AND PROCESSING (ICCP 2019), 2019, : 135 - 142
  • [23] Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing
    Zhou, Jiawei
    Naseem, Tahira
    Astudillo, Ramon Fernandez
    Lee, Young-Suk
    Florian, Radu
    Roukos, Salim
    2021 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP 2021), 2021, : 6279 - 6290
  • [24] Vietnamese Transition-based Dependency Parsing with Supertag Features
    Nguyen, Kiet V.
    Ngan Luu-Thuy Nguyen
    2016 EIGHTH INTERNATIONAL CONFERENCE ON KNOWLEDGE AND SYSTEMS ENGINEERING (KSE), 2016, : 175 - 180
  • [25] Transition-Based Dependency Parsing with Long Distance Collocations
    Zhu, Chenxi
    Qiu, Xipeng
    Huang, Xuanjing
    NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING, NLPCC 2015, 2015, 9362 : 12 - 24
  • [26] Greedy Transition-Based Dependency Parsing with Stack LSTMs
    Ballesteros, Miguel
    Dyer, Chris
    Goldberg, Yoav
    Smith, Noah A.
    COMPUTATIONAL LINGUISTICS, 2017, 43 (02) : 311 - 347
  • [27] Structured Training for Neural Network Transition-Based Parsing
    Weiss, David
    Alberti, Chris
    Collins, Michael
    Petrov, Slav
    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, : 323 - 333
  • [28] Exploring Automatic Feature Selection for Transition-Based Dependency Parsing
    Ballesteros, Miguel
    PROCESAMIENTO DEL LENGUAJE NATURAL, 2013, (51): : 119 - 126
  • [29] 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
  • [30] Graph-to-Graph Transformer for Transition-based Dependency Parsing
    Mohammadshahi, Alireza
    Henderson, James
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020,
12345