融合源端句法和语义角色信息的AMR解析

PDF(2283 KB)

中文信息学报 ›› 2019, Vol. 33 ›› Issue (8) : 36-45.

语言分析与计算

融合源端句法和语义角色信息的AMR解析

葛东来¹,李军辉¹,朱慕华²,李寿山¹,周国栋¹

作者信息 +

Modeling Source Syntax and Semantic Roles for Neural AMR Parsing

GE Donglai¹, LI Junhui¹, ZHU Muhua², LI Shoushan¹, ZHOU Guodong¹

Author information +

History +

摘要

序列到序列(seq2seq)的框架可以应用到抽象语义表示(AMR)解析任务中,把AMR解析当作一个从源端句子到目标端AMR图的翻译任务。然而,以前的工作通常把源端句子表示为一个单词序列,忽略了句子内部潜藏的句法和语义角色信息。基于seq2seq框架,该文提出了一个直接而有效的融合句法和语义角色信息的AMR解析方法。实验结果表明,该文的方法在AMR英文标准数据集上取得了6.7%的显著提升。最后,该文从多个角度深入分析了源端的句法和语义角色信息是如何对AMR解析提供帮助的。分析表明,词性信息和subword技术对AMR解析性能提升的贡献最大,上层句法和语义角色信息次之。

Abstract

Sequence-to-sequence (seq2seq) approaches formalize AMR parsing as a translation task from a source sentence to a target AMR graph. However, previous studies generally model a source sentence as a word sequence but ignore the inherent syntactic and semantic roles information. In this paper, we propose a straightforward yet effective approach to incorporate syntactic and semantic roles information of the source sentence into seq2seq based AMR parsing. Experimental results show that our approach achieves significant improvement of 6.7% F1 score on an English benchmark dataset. Further indepth analysis from various perspectives is provided to reveal how source syntactic and semantic roles information benefits AMR parsing. Experimental analysis also reveals that POS information and segmenting words into subwords make the more contribution to the improvement, followed by other syntax and semantic roles.

导出引用

葛东来,李军辉,朱慕华,李寿山,周国栋. 融合源端句法和语义角色信息的AMR解析. 中文信息学报. 2019, 33(8): 36-45

GE Donglai, LI Junhui, ZHU Muhua, LI Shoushan, ZHOU Guodong. Modeling Source Syntax and Semantic Roles for Neural AMR Parsing. Journal of Chinese Information Processing. 2019, 33(8): 36-45

参考文献

[1] Berant J,Chou A,Frostig R,et al.Semantic parsing on Freebase from question-answer pairs [C]//Proceedings of EMNLP,2013:1533-1544.
[2] Bos J,Clak S,Steedman M,et al.Wide-coverage semantic representations from a CCG parser[C]//Proceedings of COLING,2004:1240-1246.
[3] Cai Q,Yates A.Large-scale semantic parsing via schema matching and lexicon extension[C]//Proceedings of ACL,2013:423-433.
[4] Li J,Zhu M,Lu W,et al.Improving semantic parsing with enriched synchronous context-free grammar[C]//Proceddings of EMNLP,2015:1455-1465.
[5] Lewis M,Steedman M.Combined distributional and logical semantics[J].Transactions of the Association of Computational Linguistics1,2013(1):179-192.
[6] Vanderwende L,Menezes A,Quirk C.An AMR parser for English,French,German,Spanish and Japanese and a new AMR-annotated corpus[C]//Proceedings of NAACL-HLT,2015:26-30.
[7] Wong Y W,Mooney R J.Learning synchronous grammars for semantic parsing with Lambda calculus.[C]//Proceedings of ACL,2007:960-967.
[8] Barzdins G,Gosko D.RIGA at SemEval-2016 task 8:Impact of smatch extension and character-level neural translation on AMR parsing accuracy[C]//Proceedings of ACL Workshop on Semantic Evaluation (SemEval-2016),2016.
[9] Noord R.Bos J.Neural semantic parsing by character-based translation:Experiments with abstract meaning representation[J].arXiv preprint arXiv:1705.09980,2017.
[10] Konstas I,Iyer S,Yatskar M,et al.Neural AMR:Sequence-to-sequence models for parsing and generation[C]//Proceedings of ACL,2017:146-157.
[11] Peng X,Wang C,Gildea D,et al.Addressing the data sparsity issue in neural AMR parsing[C]//Proceedings of EACL,2017:366-375.
[12] Li J,Xiong D,Tu Z,et al.Modeling source syntax for neural machine translation[C]//Proceedings of ACL,2017:688-697.
[13] Shi X,Padhi I,Knight K.Does string-based neural MT learn source syntax?[C]//Proceedings of EMNLP,2016:1526-1534.
[14] Bahdanau D,Cho K,Bengio Y.Neural machine translationby jointly learning to align and translate[C]//Proceedings of ICLR,2015.
[15] Flanigan J,Thomson S,Carbonell J,et al.A.A discriminative graph-based parser for the abstract meaning representation[C]//Proceedings of ACL,2014:1426-1436.
[16] Zhou J,Xu F,Uszkoreit H,et al.AMR parsing with an incremental joint model[C]//Proceedings of EMNLP,2016:680-689.
[17] Wang C,Xue N,Pradhan S.Boosting transition-based AMR parsing with refined actions and auxiliary analyzers[C]//Proceedings of ACL,2015a:857-862.
[18] Artzi Y,Lee K,Zettlemoyer L.Broad-coverage CCG semantic parsing with AMR[C]//Proceedings of EMNLP,2015:1699-1710.
[19] Berant J,Chou A,Frostig R,et al.Semantic parsing on Freebase from question-answer pairs[C]//Proceedings of EMNLP,2013:1533-544.
[20] Pust M,Hermjakob U,Knight K,et al.Parsing English into abstract meaning representation using syntax-based machine translation[C]//Proceedings of EMNLP,2015:1143-1154.
[21] Guo Z,Lu W.Better transition-based AMR parsing with a refined search space[C]//Proceedings of EMNLP,2018:1712-1722.
[22] Peng X,Daniel G,Giorgio S.AMR parsing with cache transition systems[C]//Proceedings of AAAI,2018:4897-4904
[23] Jonas G,Matthias L,Meaghan F,et al.AMR dependency parsing with a typed semantic algebra[C]//Proceedings of ACL,2018:1831-1841.
[24] Foland W,Martin J H.Abstract meaning representation parsing using ISTM recurrent neural networks[C]//Proceedings of ACL,2017:463-472.
[25] Lyu C,Ivan T.AMR parsing as graph prediction with latent alignment[C]//Proceedings of ACL,2018:397-407.
[26] Vaswani A,Shazeer N,et al.Attention is all you need[C]//Proceedings of NIPS,2017.
[27] Vinyals O,Kaiser L,Koo T,et al.Grammar as a foreign language[C]//Proceedings of NIPS,2015.
[28] Choe D K,Charniak E.Parsing as language modeling[C]//Proceedings of EMNLP,2016:2331-2336.
[29] Gildea D,Jurafsky D.Automatic labeling of semantic roles[J].Computational Linguistics,2002,28(1):245-288.
[30] Gardner M,Grus J,Neumann M,et al.AllenNLP:A deep semantic natural language processing platform [C]//Proceedings of ACL Workshop for Natural Language Processing Open Source Software,2017.
[31] Cai S,Knight K.Smatch:An evaluation metric for semantic feature structure[C]//Proceedings of EACL,2013:748-752.
[32] Kingma D P,Ba J.Adam:A method for stochastic optimization[C]//Proceedings of ICLR,2015.
[33] Li J,Resnik P,Daumé H.Modeling syntactic and semantic structures in hierarchical phrase-based translation[C]//Proceedingsof NAACL,2013:540-549.
[34] Li J,Marton Y,Resnik P,et al.A unified model for soft linguistic reordering constraints in statistical machine translation[C]//Proceedings of ACL,2014:1123-1133.
[35] Gage Philip.A new algorithm for data compression [J].C Users Journal,1994,12(2):23-38.
[36] Sennrich R,Haddow B,Birch A.Neural machine translation of rare words with subword units[C]//Proceedings of ACL,2016:1715-1725.

基金

国家自然科学基金(61502149,61876120)

PDF(2283 KB)

761

Accesses

Citation

Detail

段落导航

摘要
Abstract
关键词
Key words
引用本文
参考文献
基金

Received	Published
2018-11-28	2019-08-20
Issue Date
2019-08-20

选择文件类型/文献管理软件名称

选择包含的内容

摘要

Abstract

关键词

Key words

引用本文

{{custom_sec.title}}

{{custom_sec.title}}

参考文献

{{custom_fnGroup.title_cn}}

脚注

基金