Skip to main content
SpringerLink
Log in

Employing Abstract Meaning Representation to Lay the Last-Mile Toward Reading Comprehension

  • Chapter
  • First Online:
Artificial Intelligence for Customer Relationship Management

Part of the book series: Human–Computer Interaction Series ((HCIS))

Abstract

We propose a Machine reading comprehension (MRC) method based on the Abstract Meaning Representation (AMR) framework and a universal graph alignment algorithm. We combine syntactic, semantic and entity-based graph representations of a question to match it with a combined representation of an answer. The alignment algorithm is applied for combining various representations of the same text as well as for matching (generalization) of two different texts such as a question and an answer. We explore a number of Question Answering (Q/A) configurations and select a scenario where the proposed AMR generalization-based algorithm AMRG detects and rectifies the errors of a traditional neural MRC. When the state-of-the-art neural MRC is applied and delivers the correct answer in almost 90% of cases, the proposed AMRG verifies each answer and if it determines that it is incorrect, attempts to find a correct one. This error-correction scenario boosts the state-of-the-art performance of a neural MRC by at least 4%.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 149.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 199.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info
Hardcover Book
USD 199.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  • Auer S, Bizer C, Kobilarov G, Lehmann J, Cyganiak R, Ives Z (2007) DBpedia: a nucleus for a web of open data. In: The semantic web, pp 722–735. Springer

    Google Scholar 

  • Banarescu L, Bonial C, Cai S, Georgesc M, Griffitt K, Hermjakob U, Knight K, Koehn P, Palmer M, Schneider N (2013) Abstract meaning representation for sembanking. In: Proceedings of the 7th linguistic annotation workshop and interoperability with discourse

    Google Scholar 

  • Bao J, Nan D, Ming Z, Tiejun Z (2014) Knowledge-based question answering as machine translation. In: ACL, pp 967–976

    Google Scholar 

  • Bollacker K, Evans C, Paritosh P, Sturge T, Taylor J (2008) Freebase: a collaboratively created graph database for structuring human knowledge. In: Proceedings of the 2008 ACM SIGMOD international conference on management of data. ACM, pp 1247–1250

    Google Scholar 

  • Bordes A, Sumit C, Jason W (2014) Question answering with subgraph embeddings. In: EMNLP, pp 615–620

    Google Scholar 

  • Burtsev M, Seliverstov A, Airapetyan R, Arkhipov M, Baymurzina D, Bushkov N, Gureenkova O, Khakhulin T, Kuratov Y, Kuznetsov D, Litinsky A, Logacheva V, Lymar A, Malykh V, Petrov M, Polulyakh V, Pugachev L, Sorokin A, Vikhreva M, Zaynutdinov M (2018) DeepPavlov: open-source library for dialogue systems. In: ACL-system demonstrations, pp 122–127

    Google Scholar 

  • Choi E, He H, Mohit I, Mark Y, Wen-tau Y, Yejin C, Percy L, Luke Z (2018) QuAC: question answering in context. In: EMNLP, pp 2174–2184

    Google Scholar 

  • Collins M, Duffy N (2002) Convolution kernels for natural language. In: Proceedings of NIPS, pp 625–632

    Google Scholar 

  • Damonte M, Shay B. Cohen (2018) Cross-lingual abstract meaning representation parsing. In: Proceedings of NAACL

    Google Scholar 

  • Damonte M, Shay B, Cohen and Giorgio Satta (2017) An incremental parser for abstract meaning representation. In: Proceedings of EACL

    Google Scholar 

  • Devlin J, Chang MW, Lee K, Toutanova K (2019) BERT: pre-training of deep bidirectional transformers for language understanding. NAACL V1

    Google Scholar 

  • Dwivedi P (2018) NLP—building a question answering model. https://towardsdatascience.com/nlp-building-a-question-answering-model-ed0529a68c54

  • Flanigan J, Thomson S, Carbonell J, Dyer C, Smith NA (2014) A discriminative graph-based parser for the abstract meaning representation. ACL 1426–1436

    Google Scholar 

  • Galitsky B (2014) Learning parse structure of paragraphs and its applications in search. Eng Appl Artif Intell 32:160–184

    Article  Google Scholar 

  • Galitsky B (2017) Matching parse thickets for open domain question answering. Data Knowl Eng 107:24–50

    Article  Google Scholar 

  • Galitsky B (2017a) Improving relevance in a content pipeline via syntactic generalization. Eng Appl Artif Intell 58:1–26

    Google Scholar 

  • Galitsky B (2019a) Building Chatbot Thesaurus, in Developing Enterprise Chatbots. Springer, Cham

    Book  Google Scholar 

  • Galitsky B (2019b) Assuring Chatbot Relevance at Syntactic Level, in Developing Enterprise Chatbots. Springer, Cham

    Book  Google Scholar 

  • Galitsky B (2012) Machine learning of syntactic parse trees for search and classification of text. Eng Appl AI 26(3):1072–1091

    Article  Google Scholar 

  • Galitsky B (2013) Transfer learning of syntactic structures for building taxonomies for search engines. Eng Appl Artif Intell 26(10):2504–2515

    Google Scholar 

  • Galitsky B, Ilvovsky D (2019) Discourse-based approach to involvement of background knowledge for question answering. Recent advances in natural language processing, pp 373–381, Varna, Bulgaria, Sep 2–4

    Google Scholar 

  • Galitsky B, Dobrocsi G, de la Rosa JL, Kuznetsov SO (2011) Using generalization of syntactic parse trees for taxonomy capture on the web. Int Conf Concept Structures, pp 104–117

    Google Scholar 

  • Galitsky B, Dobrocsi G, de la Rosa JL (2012) Inferring semantic properties of sentences mining syntactic parse trees. Data Knowl Eng 81:21–45

    Article  Google Scholar 

  • Galitsky B, Ilvovsky D, Strok F, Kuznetsov SO (2013) Improving text retrieval efficiency with pattern structures on parse thickets. In: Proceedings of FCAIR, pp 6–21

    Google Scholar 

  • Galitsky B, Ilvovsky D, Kuznetsov SO (2015) Rhetoric map of an answer to compound queries. ACL, Beijing, pp 681–686

    Google Scholar 

  • Hermann KM, KociskĂ˝ T, Grefenstette E, Espeholt L, Kay W, Suleyman M and Blunsom P (2015) Teaching machines to read and comprehend. https://arxiv.org/abs/1506.03340.

  • Ilvovsky D (2014) Using semantically connected parse trees to answer multi-sentence queries. Automatic Documentation and Mathematical Linguistics 48:33–41

    Article  Google Scholar 

  • KoÄŤiskĂ˝ T, Jonathan S, Phil B, Chris D, Karl Moritz H, Gábor M, Edward G. The NarrativeQA reading comprehension challenge. Transactions of the Association for Computational Linguistics, Volume 6, 317–328

    Google Scholar 

  • Kwiatkowski T, Eunsol C, Yoav A, Luke Z (2013) Scaling semantic parsers with on-the-fly ontology matching. In: EMNLP, pp 1545–1556, Seattle, Washington, USA

    Google Scholar 

  • Lan Z, Chen M, Goodman S, Gimpel K, Sharma P, Soricut R (2019) ALBERT: a lite bert for self-supervised learning of language representations. ArXiv, abs/1909.11942

    Google Scholar 

  • Liang P (2013) Lambda dependency-based compositional semantics. Technical report, arXiv

    Google Scholar 

  • Li B, Wen Y, Lijun B, Weiguang Q, Nianwen X (2016) Annotating the little prince with Chinese AMRs. LAW-2016, Berlin, Germany

    Google Scholar 

  • Liu Y, Myle O, Naman G, Jingfei D, Mandar J, Danqi C, Omer L, Mike L, Luke Z, Veselin S (2019) Roberta: a robustly optimized BERT pretraining approach. CoRR, https://arxiv.org/abs/1907.11692

  • Manning CD, Surdeanu M, Bauer J, Finkel J, Bethard SJ, McClosky (2014) The stanford CoreNLP natural language processing toolkit. Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pp 55–60, Baltimore, Maryland USA, June 23–24

    Google Scholar 

  • May J, Priyadarshi J (2017) SemEval-2017 Task 9: Abstract meaning representation parsing and generation. In: Proceedings of the 11th international workshop on semantic evaluation (SemEval-2017), pp 536–545

    Google Scholar 

  • Milenkovic T, PrĹľulj N (2008) Uncovering biological network function via graphlet degree signatures. Cancer Inform 6:257–273

    Article  Google Scholar 

  • Narasimhan S (2019) Nvidia clocks worlds fastest BERT training time and largest transformer based model, paving path for advanced conversational AI. https://devblogs.nvidia.com/training-bert-with-gpus/

  • Nguyen K, Tran K, Luu S, Nguyen A, Nguyen N (2020). A pilot study on multiple choice machine reading comprehension for vietnamese texts

    Google Scholar 

  • People.cn (2019) Vietnamese police detain 8 suspects in connection with illegal immigration organizing. https://en.people.cn/n3/2019/1104/c90000-9629296.html

  • Peters ME, Mark N, Mohit I, Matt G, Christopher C, Kenton L, Luke Z (2018) Deep contextualized word representations. NAACL

    Google Scholar 

  • Pourdamghani N, Gao Y, Hermjakob U, Knight K (2014) Aligning English strings with abstract meaning representation graphs. In: EMNLP, pp 425–429

    Google Scholar 

  • Rajpurkar P, Jia R, Liang P (2018) Know what you don't know: unanswerable questions for SQuAD. ACL

    Google Scholar 

  • Saltykov-Shchedrin M (1870) The history of a town (In Russian) Otechestvennye Zapiski, Saint Petersburg Russia

    Google Scholar 

  • Sidorov G, Markov, Ilia & Kolesnikova, Olga & Chanona-Hernández, Liliana (2019) Human interaction with shopping assistant robot in natural language. Journal of Intelligent and Fuzzy Systems. 36. 4889–4899. 10.3233/JIFS-179036

    Google Scholar 

  • Suchanek FM, Kasneci G, Weikum G (2007) YAGO: a core of semantic knowledge. In: Proceedings of the 16th international conference on World Wide Web. ACM, pp 697–706

    Google Scholar 

  • Wang Y, Liwei Wang, Yuanzhi Li, Di He, Wei Chen, Tie-Yan Liu (2013) A theoretical analysis of normalized discounted cumulative gain (NDCG) ranking measures. In: Proceedings of the 26th annual conference on learning theory (COLT 2013)

    Google Scholar 

  • Xue N (2019) Chinese abstract meaning representation. https://www.cs.brandeis.edu/~clp/camr/camr.html

  • Yao X, Benjamin Van Durme (2014) Information extraction over structured data: question answering with Freebase. In: Proceedings of the 52nd ACL, pp 956–966

    Google Scholar 

  • Yih W.-T, Chang M.-W, He X, and Gao J (2015) Semantic parsing via staged query graph generation: Question answering with knowledge base. In: ACL, pp 1321–1331

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Oracle Labs, Redwood Shores, CA, USA

    Boris Galitsky

Authors
  1. Boris Galitsky
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Boris Galitsky .

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Galitsky, B. (2020). Employing Abstract Meaning Representation to Lay the Last-Mile Toward Reading Comprehension. In: Artificial Intelligence for Customer Relationship Management. Human–Computer Interaction Series. Springer, Cham. https://doi.org/10.1007/978-3-030-52167-7_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-52167-7_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-52166-0

  • Online ISBN: 978-3-030-52167-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation