Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

From text to graph: a general transition-based AMR parsing using neural network

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Semantic understanding is an essential research issue for many applications, such as social network analysis, collective intelligence and content computing, which tells the inner meaning of language form. Recently, Abstract Meaning Representation (AMR) is attracted by many researchers for its semantic representation ability on an entire sentence. However, due to the non-projectivity and reentrancy properties of AMR graphs, they lose some important semantic information in parsing from sentences. In this paper, we propose a general AMR parsing model which utilizes a two-stack-based transition algorithm for both Chinese and English datasets. It can incrementally parse sentences to AMR graphs in linear time. Experimental results demonstrate that it is superior in recovering reentrancy and handling arcs while is competitive with other transition-based neural network models on both English and Chinese datasets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Zong Y, Xu G, Dolog P, Zhang Y, Liu R (2010) Co-clustering for Weblogs in Semantic Space. In: the 11th international conference of web information systems engineering, WISE 2010, Hong Kong, China, December 12–14. pp 120–127

  2. Xu G, Yu JX, Lee W (2013) Social networks and social web mining. World Wide Web Internet Web Inf Syst 16(5–6):541–544

    Article  Google Scholar 

  3. Li C, Goldwasser D (2019) Encoding social information with graph convolutional networks for political perspective detection in news media. In: the 57th conference of the association for computational linguistics, ACL 2019, Florence, Italy, July 28–August 2, pp 2594–2604

  4. Islam J, Mercer RE, Xiao L (2019) Multi-Channel convolutional neural network for twitter emotion and sentiment recognition. In: the 2019 conference of the north American chapter of the association for computational linguistics: human language technologies, NAACL-HLT 2019, Minneapolis, MN, USA, June 2–7, pp 1355–1365

  5. Gupta I, Joshi N (2020) Enhanced twitter sentiment analysis using hybrid approach and by accounting local contextual semantic. J Intell Syst 29(1):1611–1625

    Article  Google Scholar 

  6. Rudnik C, Ehrhart T, Ferret O, Teyssou D, Troncy R,Tannier X (2019) Searching news articles using an event knowledge graph leveraged by Wikidata. In: Companion of the 2019 world wide web conference, WWW 2019, San Francisco, CA, USA, May 13–17, pp 1232–1239

  7. Wang H, Xu T, Liu Q, Lian D, Chen E, Du D, Wu H, Su W (2019) Mcne: an end-to-end framework for learning multiple conditional network representations of social network. In: the 25th ACM SIGKDD international conference on knowledge discovery & data mining, KDD 2019, Anchorage, AK, USA, August 4–8, pp 1064–1072

  8. Yang C, Zhang J, Wang H, Li S, Kim M, Walker M, Han J (2020) Relation learning on social networks with multi-modal graph edge variational autoencoders. In: The thirteenth ACM international conference on web search and data mining, WSDM 2020, Houston, TX, USA, February 3–7, pp 2328–2337

  9. Wang Y, Sun H, Zhao Y, Zhou W, Zhu S (2019) A heterogeneous graph embedding framework for location-based social network analysis in smart cities. IEEE Trans Ind Inf 16(4):2747–2755

    Google Scholar 

  10. Zhang J, Tan L, Tao X, Wang D, Ying JJ, Wang X (2019) Learning relational fractals for deep knowledge graph embedding in online social networks. In: 20th international conference on web information systems engineering, WISE 2019, Hong Kong, China, November 26–30, pp 660–674

  11. Xie T, France-Lanord A, Wang Y, Shao-Horn Y, Grossman JC (2019) Graph dynamical networks for unsupervised learning of atomic scale dynamics in materials. Nature Commun 10(1):2667

    Article  Google Scholar 

  12. Jin W, Barzilay R, Jaakkola TS (2018) Junction tree variational autoencoder for molecular graph generation. In: the 35th International conference on machine learning, ICML 2018, Stockholmsmässan, Stockholm, Sweden, July 10–15, pp 1–13

  13. Jin W, Yang KK, Barzilay R, Jaakkola TS (2019) Learning Multimodal Graph-to-Graph Translation for Molecule Optimization. In: 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6–9, pp 2328–2337

  14. Wang S, Li Z, Zhang S, Jiang M, Wang X, Wei Z (2020) Molecular property prediction based on a multichannel substructure graph. IEEE Access 8:18601–18614

    Article  Google Scholar 

  15. Samanta B, Abir DE, Jana G, Chattaraj PK, Ganguly N, Rodriguez MG (2018) A deep generative model for molecular graphs. In: The Thirty-Third AAAI conference on artificial intelligence, AAAI 2019, Honolulu, Hawaii, USA, January 27–February 1, pp 2328–2337

  16. Zettlemoyer LS, Collins M (2005) Learning to map sentences to logical form: structured classification with probabilistic categorial grammars. In: the 21st conference in uncertainty in artificial intelligence, UAI 2005, Edinburgh, Scotland, July 26–29, pp 658–666

  17. Wong YW, Mooney RJ (2006) Learning for semantic parsing with statistical machine translation. In: Human language technology conference of the North American chapter of the association of computational linguistics, New York, USA, June 4–9, pp 439–446

  18. Banarescu L, Bonial C, Cai S, Georgescu M, Griffitt K, Hermjakob U, Knight K, Koehn P, Palmer M, Schneider N (2013) Abstract meaning representation for sembanking. In: the 7th linguistic annotation workshop and interoperability with discourse, LAW-ID@ACL 2013, Sofia, Bulgaria, August 8–9, pp 178–186

  19. Liu F, Flanigan J, Thomson S, Sadeh NM, Smith NA (2015) Toward abstractive summarization using semantic representations. In: the 2015 conference of the North American chapter of the association for computational linguistics: human language technologies, , NAACL-HLT 2015, Denver, Colorado, USA, May 31–June 5, pp 1077–1086

  20. Garg S, Galstyan A, Hermjakob U, Marcu D (2016) Extracting biomolecular interactions using semantic parsing of biomedical text. In: The Thirtieth AAAI conference on artificial intelligence, AAAI 2016, Phoenix, Arizona, USA, February 12–17, pp 2718–2726

  21. Sachan M, Xing EP (2016) Machine comprehension using rich semantic representations. In: the 54th annual meeting of the association for computational linguistics, ACL 2016, Berlin, Germany, August 7–12, pp 486–492

  22. Huang L, Ji H, Cho K, Dagan I, Riedel S, Voss CR (2018) Zero-shot transfer learning for event extraction. In: the 56th annual meeting of the association for computational linguistics, ACL 2018, Melbourne, Australia, July 15–20, pp 2160–2170

  23. Song L, Gildea D, Zhang Y, Wang Z, Su J (2019) Semantic neural machine translation using AMR. Trans Assoc Comput Linguistics 7:19–31

    Article  Google Scholar 

  24. Takase S, Suzuki J, Okazaki N, Hirao T, Nagata M (2016) Neural headline generation on abstract meaning representation. In: the 2016 conference on empirical methods in natural language processing, EMNLP 2016, Austin, Texas, USA, November 1–4. pp 1054–1059

  25. Chen WT (2015) Learning to map dependency parses to abstract meaning representations. In: the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing of the Asian federation of natural language processing, ACL 2015, Beijing, China, July 26–31. pp 41–46

  26. Wang C, Pradhan S, Pan XM, Ji H, Xue NW (2016) CAMR at SemEval-2016 task 8: An extended transition-based AMR parser. In: the 10th international workshop on semantic evaluation, SemEval@NAACL-HLT 2016, San Diego, CA, USA, June 16–17, pp 1173–1178

  27. Titov I, Lyu C (2018) AMR parsing as graph prediction with latent alignment. In: the 56th annual meeting of the association for computational linguistics, ACL 2018, Melbourne, Australia, July 15–20. pp 397–407

  28. Wang C, Xue NW, Pradhan S (2015) Boosting transition-based AMR parsing with refined actions and auxiliary analyzers. In: the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing of the Asian federation of natural language processing, ACL 2015, Beijing, China, July 26–31, pp 857–862

  29. Goodman J, Vlachos A, Naradowsky J (2016) Noise reduction and targeted exploration in imitation learning for abstract meaning representation parsing. In: the 54th annual meeting of the association for computational linguistics, ACL 2016, Berlin, Germany, August 7–12, pp 1–11

  30. Wang C, Xue NW, Pradhan S (2015) A transition-based algorithm for AMR parsing. In: Human language technology conference of the north American chapter of the association of computational linguistics, NAACL-HLT 2015, Denver, Colorado, USA, May 31–June 5, pp 366–375

  31. Werling K, Angeli G, Manning C (2015) Robust subgraph generation improves abstract meaning representation parsing. In: the 53rh annual meeting of the association for computational linguistics, ACL 2015, Beijing, China, July 26–31, pp 982–991

  32. Wang C, Xue NW (2017) Getting the most out of AMR parsing. In: the 2017 conference on empirical methods in natural language processing, EMNLP 2017, Copenhagen, Denmark, September 9–11, pp 1257–1268

  33. Damonte M, Cohen SB, Satta G (2017) An incremental parser for abstract meaning representation. In: the 15th conference of the European chapter of the association for computational linguistics, EACL 2017, Valencia, Spain, April 3–7, pp 536–546

  34. Buys J, Blunsom P (2017) Robust incremental neural semantic graph parsing. In: the 55th annual meeting of the association for computational linguistics, ACL 2017, Vancouver, Canada, July 30–August 4, pp 1215–1226

  35. Ballesteros M, Onaizan Y (2017) AMR parsing using stack-LSTMs. In: the 2017 conference on empirical methods in natural language processing, EMNLP 2017, Copenhagen, Denmark, September 9–11, pp 1269–1275

  36. Wang C, Li B, Xue NW (2018) Transition-based chinese AMR parsing. In: Human language technology conference of the north American chapter of the association of computational linguistics, NAACL-HLT 2018, New Orleans, Louisiana, USA, June 1–6, pp 247–252

  37. Guo Z, Lu W (2018) Better transition-based AMR parsing with refined search space. In: the 2018 conference on empirical methods in natural language processing, EMNLP 2018, Brussels, Belgium, October 31–November 4, pp 1712–1722

  38. Zhang H, Li J, Ji Y, Yue H (2017) Understanding subtitles by character-level sequence-to-sequence learning. IEEE Trans Ind Inf 13(2):616–624

    Article  Google Scholar 

  39. Qu WG, Zhou JS, Wu XD, Dai R, Gu M, Gu Y (2017) Survey on abstract meaning representation. J Data Acquis Process 32(1):26–36

    Google Scholar 

  40. Li B, Wen Y, Qu WG, Bu LJ, Xue NW (2016) Annotating the little prince with Chinese AMRs. In: the 10th linguistic annotation workshop and interoperability with discourse, LAW 2016, Berlin, Germany, August 11, pp 7–15

  41. Kingsbury P, Palmer M (2002) From Treebank to Propbank. In: The third international conference on language resources and evaluation, LREC 2002, Las Palmas, Canary Islands, Spain, May 29–31, pp 1989–1993

  42. Flanigan J, Thomson S, Carbonell JG, Dyer C, Smith NA (2014) A discriminative graph-based parser for the abstract meaning representation. In: the 52nd annual meeting of the association for computational linguistics, ACL 2014, Baltimore, MD, USA, June 22–27, pp 1426–1436

  43. Zhou JS, Xu FY, Uszkoreit H, Qu WG, Li R, Gu YH (2016) AMR parsing with an incremental joint model. In: the 2016 conference on empirical methods in natural language processing, EMNLP 2016, Austin, Texas, USA, November 1–4, pp 680–689

  44. Foland W, Martin JH (2016) CU-NLP at SemEval-2016 Task 8: AMR parsing using LSTM based recurrent neural networks. In: the 10th international workshop on semantic evaluation, SemEval@NAACL-HLT 2016, San Diego, CA, USA, June 16–17, pp 1197–1201

  45. Foland W, Martin JH (2016) Abstract meaning representation parsing using LSTM recurrent neural networks. In: the 55th annual meeting of the association for computational linguistics, ACL 2017, Vancouver, Canada, July 30–August 4, pp 463–472

  46. Puzikov Y, Kawahara D, Kurohashi S (2016) M2L at SemEval-2016 Task 8: AMR parsing with neural networks. In: International workshop on semantic evaluations, SemEval@NAACL-HLT 2016, San Diego, CA, USA, June 16–17, pp 1154–1159

  47. Artzi Y, Lee K, Zettlemoyer L (2015) Broad-coverage CCG semantic parsing with AMR. In: Empirical methods in natural language processing, EMNLP 2015, Lisbon, Portugal, September 17–21, pp 1699–1710

  48. Kwiatkowski T, Zettlemoyer L, Goldwater S, Steedman M (2011) Lexical generalization in CCG grammar induction for semantic parsing. In: Empirical methods in natural language processing, EMNLP 2011, Edinburgh, UK, July 27–31, pp 127–129

  49. Misra DK, Artzi Y (2016) Neural shift-reduce CCG semantic parsing. In: the 2016 conference on empirical methods in natural language processing, EMNLP 2016, Austin, Texas, USA, November 1–4, pp 1775–1778

  50. Pust M, Hermjakob U, Knight K et al (2015) Using syntax-based machine translation to parse english into abstract meaning representation. CoRR abs/1504.06665

  51. Zhang S, Ma X, Duh K, Van Durme B (2019) AMR parsing as sequence-to-graph transduction. In: the 57th conference of the association for computational linguistics, ACL 2019, Florence, Italy, July 28–August 2, pp 80–94

  52. Gildea D, Xue NW, Peng XC, Wang C (2017) Addressing the data sparsity issue in neural AMR parsing. In: the 15th conference of the European chapter of the association for computational linguistics, EACL 2017, Valencia, Spain, April 3–7, pp 366–375

  53. Barzdins G, Gosko D (2016) RIGA at SemEval-2016 Task 8: Impact of smatch extensions and character-level neural translation on AMR parsing accuracy. In: International workshop on semantic evaluations, SemEval@NAACL-HLT 2016, San Diego, CA, USA, June 16–17, pp 1143–1147

  54. Konstas I, Iyer S, Yatskar M, et al (2017) Neural AMR: sequence-to-sequence models for parsing and generation. In: the 55th annual meeting of the association for computational linguistics, ACL 2017, Vancouver, Canada, July 30–August 4, pp 146–157

  55. Nivre J (2004) Incrementality in Deterministic dependency parsing. In: the ACL workshop incremental parsing: bringing engineering and cognition together, ACL 2004, Barcelona, Spain, July 21–26, pp 50–57

  56. Nivre J (2008) Algorithms for deterministic incremental dependency parsing. Comput Linguist 34(5):513–553

    Article  MathSciNet  Google Scholar 

  57. Sagae K, Tsujii J (2008) Shift-reduce dependency DAG parsing. In: the 22nd international conference on computational linguistics, COLING 2008, Manchester, UK, August 18–22, pp 753–760

  58. Zhang X, Du Y, Sun W et al (2016) Transition-based parsing for deep dependency structures. Comput Linguist 42(3):353–389

    Article  MathSciNet  Google Scholar 

  59. Li B, Wen Y, Song L, Bu LJ, Qu WG, Xue NW (2017) Construction of Chinese abstract meaning representation corpus with concept-to-word alignment. J Chin Inf Process 31(6):93–102

    Google Scholar 

  60. Cai S, Knight K (2013) Smatch: an evaluation metric for semantic feature structures. In: the 51st annual meeting of the association for computational linguistics, ACL 2013, Sofia, Bulgaria, August 4–9, pp 748–752

Download references

Acknowledgements

This work was supported by the Ministry of Education of Humanities and Social Science project under Grant 16YJC790123 and National Natural Science Foundation of China under Grant 61772278.

Author information

Authors and Affiliations

  1. School of Computer Science and Technology, Nanjing Normal University, Nanjing, China

    Min Gu, Yanhui Gu, Junsheng Zhou & Weiguang Qu

  2. School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing, China

    Weilan Luo

  3. Advanced Analytics Institute, University of Technology Sydney, Sydney, Australia

    Guandong Xu

  4. Institute of Big Data, College of Computer Science, Nankai University, Tianjin, China

    Zhenglu Yang

Authors
  1. Min Gu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yanhui Gu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Weilan Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Guandong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhenglu Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Junsheng Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Weiguang Qu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Yanhui Gu or Zhenglu Yang.

Ethics declarations

Conflicts of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gu, M., Gu, Y., Luo, W. et al. From text to graph: a general transition-based AMR parsing using neural network. Neural Comput & Applic 33, 6009–6025 (2021). https://doi.org/10.1007/s00521-020-05378-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-020-05378-5

Keywords

Search

Navigation