Learning compositional structures for semantic graph parsing

被引:0
|
作者
Groschwitz, Jonas [1 ]
Fowlie, Meaghan [2 ]
Koller, Alexander [1 ]
机构
[1] Saarland Univ, Saarbrucken, Germany
[2] Univ Utrecht, Utrecht, Netherlands
基金
荷兰研究理事会;
关键词
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
AM dependency parsing is a method for neural semantic graph parsing that exploits the principle of compositionality. While AM dependency parsers have been shown to be fast and accurate across several graphbanks, they require explicit annotations of the compositional tree structures for training. In the past, these were obtained using complex graphbank-specific heuristics written by experts. Here we show how they can instead be trained directly on the graphs with a neural latent-variable model, drastically reducing the amount and complexity of manual heuristics. We demonstrate that our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training, greatly facilitating the use of AM dependency parsing for new sembanks.
引用
收藏
页码:22 / 32
页数:11
相关论文
共 50 条
  • [1] Learning compositional structures for semantic graph parsing Supplementary Materials
    Groschwitz, Jonas
    Fowlie, Meaghan
    Koller, Alexander
    [J]. SPNLP 2021: THE 5TH WORKSHOP ON STRUCTURED PREDICTION FOR NLP, 2021, : 33 - 36
  • [2] Improving Compositional Generalization in Semantic Parsing
    Oren, Inbar
    Herzig, Jonathan
    Gupta, Nitish
    Gardner, Matt
    Berant, Jonathan
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EMNLP 2020, 2020, : 2482 - 2495
  • [3] Compositional Semantic Parsing Across Graphbanks
    Lindemann, Matthias
    Groschwitz, Jonas
    Koller, Alexander
    [J]. 57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 4576 - 4585
  • [4] SUBS: Subtree Substitution for Compositional Semantic Parsing
    Yang, Jingfeng
    Zhang, Le
    Yang, Diyi
    [J]. NAACL 2022: THE 2022 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES, 2022, : 169 - 174
  • [5] Learning for semantic parsing
    Mooney, Raymond J.
    [J]. COMPUTATIONAL LINGUISTICS AND INTELLIGENT TEXT PROCESSING, 2007, 4394 : 311 - 324
  • [6] Deep Learning of Knowledge Graph Embeddings for Semantic Parsing of Twitter Dialogs
    Heck, Larry
    Huang, Hongzhao
    [J]. 2014 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), 2014, : 597 - 601
  • [7] Semantic Object Parsing with Graph LSTM
    Liang, Xiaodan
    Shen, Xiaohui
    Feng, Jiashi
    Lin, Liang
    Yan, Shuicheng
    [J]. COMPUTER VISION - ECCV 2016, PT I, 2016, 9905 : 125 - 143
  • [8] Compositional Generalization in Multilingual Semantic Parsing over Wikidata
    Cui, Ruixiang
    Aralikatte, Rahul
    Lent, Heather
    Hershcovich, Daniel
    [J]. TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, 2022, 10 : 937 - 955
  • [9] Compositional Semantic Parsing on Semi-Structured Tables
    Pasupat, Panupong
    Liang, Percy
    [J]. 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, : 1470 - 1480
  • [10] Span-based Semantic Parsing for Compositional Generalization
    Herzig, Jonathan
    Berant, Jonathan
    [J]. 59TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 11TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING, VOL 1 (ACL-IJCNLP 2021), 2021, : 908 - 921