{"type":"ScholarlyArticle","title":"Modeling Source Syntax and Semantics for Neural AMR Parsing","authors":[{"name":"DongLai Ge","slug":"donglai-ge","given":"DongLai","family":"Ge","affiliation":"School of Computer Science and Technology , Soochow University , Suzhou , China"},{"name":"Junhui Li","slug":"junhui-li","given":"Junhui","family":"Li","affiliation":"School of Computer Science and Technology , Soochow University , Suzhou , China"},{"name":"Muhua Zhu","slug":"muhua-zhu","given":"Muhua","family":"Zhu","affiliation":"Alibaba Group , Hangzhou , China"},{"name":"Shoushan Li","slug":"shoushan-li","given":"Shoushan","family":"Li","affiliation":"School of Computer Science and Technology , Soochow University , Suzhou , China"}],"abstract":"Sequence-to-sequence (seq2seq) approaches formalize Abstract Meaning Representation (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 information in the sentence. In this paper, we propose two effective approaches to explicitly modeling source syntax and semantics into neural seq2seq AMR parsing. The first approach linearizes source syntactic and semantic structure into a mixed sequence of words, syntactic labels, and semantic labels, while in the second approach we propose a syntactic and semantic structure-aware encoding scheme through a self-attentive model to explicitly capture syntactic and semantic relations between words. Experimental results on an English benchmark dataset show that our two approaches achieve significant improvement of 3.1% and 3.4% F1 scores over a strong seq2seq baseline.","doi":"10.24963/ijcai.2019/691","url":"https://ijcai.org/proceedings/2019/691","pdf":"https://ijcai.org/proceedings/2019/0691.pdf","markdown":"https://ijcai.org/proceedings/2019/691.md","bibtex":"https://ijcai.org/proceedings/2019/bibtex/691","volume":{"slug":"2019","title":"Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2019","url":"https://ijcai.org/proceedings/2019/","year":2019,"location":"Macao","dates":"10-16 August 2019","editors":"Sarit Kraus","isbn":"978-0-9992411-4-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2019"},"section":"Natural Language Processing","track":"Main track","number":691,"pages":{"first":4975,"last":4981},"keywords":["Natural Language Processing: Natural Language Semantics","Natural Language Processing: Tagging, chunking, and parsing"],"videos":[],"references":[{"position":1,"raw":"[Artzi et al., 2015] Yoav Artzi, Kenton Lee, and Luke Zettle- moyer. Broad-coverage ccg semantic parsing with amr. In Proceedings of EMNLP, pages 1699-1710, 2015.","title":"Broad-coverage ccg semantic parsing with amr","authors":"Yoav Artzi, Kenton Lee, Luke Zettlemoyer","year":"2015","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Ballesteros and Al-Onaizan, 2017] Miguel Ballesteros and Yaser Al-Onaizan. Amr parsing using stack-lstms. In Pro- ceedings of EMNLP, page 1269-1275, 2017.","title":"Miguel Ballesteros and Yaser Al-Onaizan. Amr parsing using stack-lstms","authors":"Al-Onaizan Ballesteros","year":"2017","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Barzdins and Gosko, 2016] Guntis Barzdins and Didzis Gosko. RIGA at SemEval-2016 task 8: Impact of smatch extension and character-level neural translation on amr parsing accuracy. In Proceedings of SemEval, page 1143-1147, 2016.","title":"Guntis Barzdins and Didzis Gosko. RIGA at SemEval-2016 task 8: Impact of smatch extension and character-level neural translation on amr parsing accuracy","authors":"Gosko Barzdins","year":"2016","venue":"Proceedings of SemEval","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Buys and Blunsom, 2017] Jan Buys and Phil Blunsom. Ox- ford at semeval2017 task 9: Neural AMR parsing with pointer-augmented attention. In Proceedings of SemEval, page 914-919, 2017.","title":"Oxford at semeval2017 task 9: Neural AMR parsing with pointer-augmented attention","authors":"Blunsom Buys, Jan Buys, Phil Blunsom","year":"2017","venue":"Proceedings of SemEval","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cai and Knight, 2013] Shu Cai and Kevin Knight. Smatch: an evaluation metric for semantic feature structure. In Pro- ceedings of EACL, pages 748-752, 2013.","title":"Smatch: an evaluation metric for semantic feature structure","authors":"Knight ; ] Shu Cai, Kevin Cai, Knight","year":"2013","venue":"Proceedings of EACL","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Choe and Charniak, 2016] Do Kook Choe and Eugene Charniak. Parsing as language modeling. In Proceedings of EMNLP, pages 2331-2336, 2016.","title":"Parsing as language modeling","authors":"Charniak ; Choe, Kook Do, Eugene Choe, Charniak","year":"2016","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Damonte et al., 2017] Marco Damonte, Shay B. Cohen, and Giorgio Satta. An incremental parser for abstract meaning representation. In Proceedings of EACL, pages 536-546, 2017.","title":"An incremental parser for abstract meaning representation","authors":"Marco Damonte, Shay B Cohen, Giorgio Satta","year":"2017","venue":"Proceedings of EACL","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Flanigan et al., 2014] Jeffrey Flanigan, Sam Thomson, Jaime Carbonell, Chris Dyer, and Noah A. Smith. A dis- criminative graph-based parser for the abstract meaning representation. In Proceedings of ACL, pages 1426-1436, 2014.","title":"A discriminative graph-based parser for the abstract meaning representation","authors":"Jeffrey Flanigan, Sam Thomson, Jaime Carbonell, Chris Dyer, Noah A Smith","year":"2014","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Foland and Martin, 2017] William Foland and James H. Martin. Abstract meaning representation parsing using lstm recurrent neural networks. In Proceedings of ACL, pages 463-472, 2017.","title":"Abstract meaning representation parsing using lstm recurrent neural networks","authors":"William Foland, James H Martin","year":"2017","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gardner et al., 2017] Matt Gardner, Joel Grus, Mark Neu- mann, Oyvind Tafjord, Pradeep Dasigi, Nelson Liu, Matthew Peters, Michael Schmitz, and Luke Zettlemoyer. AllenNLP: A deep semantic natural language processing platform. In Proceedings of ACL Workshop for NLP Open Source Software, pages 1-6, 2017.","title":"AllenNLP: A deep semantic natural language processing platform","authors":"Matt Gardner, Joel Grus, Mark Neumann, Oyvind Tafjord, Pradeep Dasigi, Nelson Liu, Matthew Peters, Michael Schmitz, Luke Zettlemoyer","year":"2017","venue":"Proceedings of ACL Workshop for NLP Open Source Software","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Gildea and Jurafsky, 2002] Daniel Gildea and Daniel Juraf- sky. Automatic labeling of semantic roles. Computational Linguistics, 28:245-288, 2002.","title":"Automatic labeling of semantic roles","authors":"Jurafsky Gildea","year":"2002","venue":"Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Groschwitz et al., 2018] Jonas Groschwitz, Matthias Linde- mann, Meaghan Fowlie, Mark Johnson, and Alexander Koller. AMR dependency parsing with a typed semantic algebra. In Proceedings of ACL, pages 1831-1841, 2018.","title":"AMR dependency parsing with a typed semantic algebra","authors":"Groschwitz","year":"2018","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Guo and Lu, 2018] Zhijiang Guo and Wei Lu. Better transition-based AMR parsing with a refined search space. In Proceedings of EMNLP, pages 1712-1722, 2018.","title":"Better transition-based AMR parsing with a refined search space","authors":"Lu ; ] Zhijiang Guo, Wei Guo, Lu","year":"2018","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kingma and Ba, 2015] Diederik P. Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In Proceed- ings of ICLR, 2015.","title":"Adam: A method for stochastic optimization","authors":"P Diederik, Jimmy Kingma, Ba","year":"2015","venue":"Proceedings of ICLR","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Koehn, 2004] Philipp Koehn. Statistical significance tests for machine translation evaluation. In Proceedings of EMNLP, pages 388-395, 2004.","title":"Statistical significance tests for machine translation evaluation","authors":"Philipp Koehn, Koehn","year":"2004","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Konstas et al., 2017] Ioannis Konstas, Srinivasan Iyer, Mark Yatskar, Yejin Choi, and Luke Zettlemoyer. Neural AMR: Sequence-to-sequence models for parsing and generation. In Proceedings of ACL, pages 146-157, 2017.","title":"Neural AMR: Sequence-to-sequence models for parsing and generation","authors":"Ioannis Konstas, Srinivasan Iyer, Mark Yatskar, Yejin Choi, Luke Zettlemoyer","year":"2017","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Li et al., 2014] Junhui Li, Yuval Marton, Philip Resnik, and Hal Daumé III. A unified model for soft linguistic reorder- ing constraints in statistical machine translation. In Pro- ceedings of ACL, pages 1123-1133, 2014.","title":"A unified model for soft linguistic reordering constraints in statistical machine translation","authors":"Junhui Li, Yuval Marton, Philip Resnik, Hal Daumé, Iii","year":"2014","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li et al., 2017] Junhui Li, Deyi Xiong, Zhaopeng Tu, Muhua Zhu, Min Zhang, and Guodong Zhou. Modeling source syntax for neural machine translation. In Proceed- ings of ACL, pages 688-697, 2017.","title":"Modeling source syntax for neural machine translation","authors":"Junhui Li, Deyi Xiong, Zhaopeng Tu, Muhua Zhu, Min Zhang, Guodong Zhou","year":"2017","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Lyu and Titov, 2018] Chunchuan Lyu and Ivan Titov. AMR parsing as graph prediction with latent alignment. In Pro- ceedings of ACL, page 397-407, 2018.","title":"AMR parsing as graph prediction with latent alignment","authors":"Titov Lyu, Chunchuan Lyu, Ivan Titov","year":"2018","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Peng et al., 2017] Xiaochang Peng, Chuang Wang, Daniel Gildea, and Nianwen Xue. Addressing the data sparsity issue in neural AMR parsing. In Proceedings of EACL, pages 366-375, 2017.","title":"Addressing the data sparsity issue in neural AMR parsing","authors":"Peng","year":"2017","venue":"Proceedings of EACL","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Peng et al., 2018] Xiaochang Peng, Daniel Gildea, and Giorgio Satta. Amr parsing with cache transition systems. In Proceedings of AAAI, page 4897-4904, 2018.","title":"Amr parsing with cache transition systems","authors":"Peng","year":"2018","venue":"Proceedings of AAAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Pust et al., 2015] Michael Pust, Ulf Hermjakob, Kevin Knight, Daniel Marcu, and Jonathan May. Parsing english into abstract meaning representation using syntax-based machine translation. In Proceedings of EMNLP, pages 1143-1154, 2015.","title":"Parsing english into abstract meaning representation using syntax-based machine translation","authors":"Michael Pust, Ulf Hermjakob, Kevin Knight, Daniel Marcu, Jonathan May","year":"2015","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Sennrich et al., 2016] Rico Sennrich, Barry Haddow, and Alexandra Birch. Neural machine translation of rare words with subword units. In Proceedings of ACL, pages 1715- 1725, 2016.","title":"Neural machine translation of rare words with subword units","authors":"Sennrich","year":"2016","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Shaw et al., 2018] Peter Shaw, Jakob Uszkoreit, and Ashish Vaswani. Self-attention with relative position representa- tions. In Proceedings of NAACL, pages 464-468, 2018.","title":"Self-attention with relative position representations","authors":"Peter Shaw, Jakob Uszkoreit, Ashish Vaswani","year":"2018","venue":"Proceedings of NAACL","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Shi et al., 2016] Xing Shi, Inkit Padhi, and Kevin Knight. Does string-based neural MT learn source syntax? In Pro- ceedings of EMNLP, pages 1526-1534, 2016.","title":"Does string-based neural MT learn source syntax?","authors":"Xing Shi, Inkit Padhi, Kevin Knight","year":"2016","venue":"Proceedings of EMNLP","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[van Noord and Bos, 2017] Rik van Noord and Johan Bos. Neural semantic parsing by character-based translation: Experiments with abstract meaning representation. Com- putational Linguistics in the Netherlands Journal, 7:93- 108, 2017.","title":"Neural semantic parsing by character-based translation: Experiments with abstract meaning representation","authors":"Van Noord, ; ] Rik Bos, Johan Van Noord, Bos","year":"2017","venue":"Computational Linguistics in the Netherlands Journal","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N.Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. In Proceedings of NIPS, pages 5998-6008, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Proceedings of NIPS","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Vilares and Gómez-Rodríguez, 2018] David Vilares and Carlos Gómez-Rodríguez. A transition-based algorithm for unrestricted amr parsing. In Proceedings of NAACL, pages 142-149, 2018.","title":"David Vilares and Carlos Gómez-Rodríguez. A transition-based algorithm for unrestricted amr parsing","authors":"Gómez-Rodríguez Vilares","year":"2018","venue":"Proceedings of NAACL","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Vinyals et al., 2015] Oriol Vinyals, Lukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, and Geoffrey Hinton. Grammar as a foreign language. In Proceedings of NIPS, pages 2773-2781, 2015.","title":"Grammar as a foreign language","authors":"Oriol Vinyals, Lukasz Kaiser, Terry Koo, Slav Petrov, Ilya Sutskever, Geoffrey Hinton","year":"2015","venue":"Proceedings of NIPS","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wang et al., 2015a] Chuan Wang, Nianwen Xue, and Sameer Pradhan. Boosting transition-based amr parsing with refined actions and auxiliary analyzers. In Proceed- ings of ACL, pages 857-862, 2015.","title":"Boosting transition-based amr parsing with refined actions and auxiliary analyzers","authors":"Wang","year":"2015","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Wang et al., 2015b] Chuan Wang, Nianwen Xue, and Sameer Pradhan. A transition-based algorithm for amr parsing. In Proceedings of NAACL, pages 366-375, 2015.","title":"A transition-based algorithm for amr parsing","authors":"Wang","year":"2015","venue":"Proceedings of NAACL","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Werling et al., 2015] Keenon Werling, Gabor Angeli, and Christopher D. Manning. Robust subgraph generation im- proves abstract meaning representation parsing. In Pro- ceedings of ACL, page 982-991, 2015.","title":"Robust subgraph generation improves abstract meaning representation parsing","authors":"Keenon Werling, Gabor Angeli, Christopher D Manning","year":"2015","venue":"Proceedings of ACL","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}