Abstract Meaning Representations as Linked Data

  • Gully A. Burns
  • Ulf Hermjakob
  • José Luis Ambite
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9982)

Abstract

The complex relationship between natural language and formal semantic representations can be investigated by the development of large, semantically-annotated corpora. The “Abstract Meaning Representation” (AMR) formulation describes the semantics of a whole sentence as a rooted, labeled graph, where nodes represent concepts/entities (such as PropBank frames and named entities) and edges represent relations between concepts (such as verb roles). AMRs have been used to annotate corpora of classic books, newstext and biomedical literature. Research on semantic parsers that generate AMRs from text is progressing rapidly. In this paper, we describe an AMR corpus as Linked Data (AMR-LD) and the techniques used to generate it (including an open-source implementation). We discuss the benefits of AMR-LD, including convenient analysis using SPARQL queries and ontology inferences enabled by embedding into the web of Linked Data, as well as the impact of semantic web representations directly derived from natural language.

Keywords

Linked linguistic data Abstract Meaning Representation AMR Sembank Biological pathways 

References

  1. 1.
    Banarescu, L., Bonial, C., Cai, S., Georgescu, M., Griffitt, K., Hermjakob, U., Knight, K., Koehn, P., Palmer, M., Schneider, N.: Abstract meaning representation for sembanking. In: Proceedings of the 7th Linguistic Annotation Workshop and Interoperability with Discourse, pp. 178–186, Sofia, Bulgaria, Assoc. Computational Linguistics (2013)Google Scholar
  2. 2.
    Bergeron, S., et al.: The serine protease inhibitor serpinE2 is a novel target of ERK signaling involved in human colorectal tumorigenesis. Mol. Cancer 9, 271 (2010)CrossRefGoogle Scholar
  3. 3.
  4. 4.
    Vanderwende, L., et al.: An AMR parser for English, French, German, Spanish and Japanese and a new AMR-annotated corpus. In: NAACL Demonstrations, pp. 26–30. ACL (2015). http://www.aclweb.org/anthology/N15-3006
  5. 5.
    Flanigan, J., et al.: Generation from abstract meaning representation using tree transducers. In: NAACL: Human Language Technologies, pp. 731–739. ACL (2016). http://www.aclweb.org/anthology/N16-1087
  6. 6.
    Rao, S., Vyas, Y., Daume, H., Resnick, P.: Parser for abstract meaning representation using learning to search. In: Proceedings of SemEval 2016 (2016)Google Scholar
  7. 7.
    AMR project website. http://amr.isi.edu/
  8. 8.
    Cohen, P.R.: DARPA’s big mechanism program. Phys. Biol. 12(4), 045008 (2015)CrossRefGoogle Scholar
  9. 9.
    Naumann, F., Herschel, M.: An Introduction to Duplicate Detection. Morgan and Claypool Publishers, New York (2010)MATHGoogle Scholar
  10. 10.
    Palmer, M., Gildea, D., Kingsbury, P.: The proposition bank: an annotated corpus of semantic roles. Comput. Linguist. 31(1), 71–106 (2005)CrossRefGoogle Scholar
  11. 11.
    Pfam: home page. http://pfam.xfam.org
  12. 12.
  13. 13.
    Pathway commons homepage. http://www.pathwaycommons.org/
  14. 14.
    Jurczyk, P., Lu, J.J., Xiong, L., Cragan, J.D., Correa, A.: FRIL: a tool for comparative record linkage. AMIA Ann. Symp. Proc. 2008, 440–444 (2008)Google Scholar
  15. 15.
    AMR-linked data github repository. https://github.com/BMKEG/amr-ld/
  16. 16.
    L2K2R2 bioentity mapping web service. http://dna.isi.edu:7080/grounding/
  17. 17.
    Burns, G., Ambite, J.L., Hermjakob, U., The AMR Development Team: Biomedical abstract meaning representation as linked data (v0.8.1). figshare (2016). https://dx.doi.org/10.6084/m9.figshare.3206062.v1
  18. 18.
    Cimiano, P., Unger, C., McCrae, J.P.: Ontology-Based Interpretation of Natural Language. Synthesis Lectures on Human Language Technologies. Morgan & Claypool Publishers, New York (2014)Google Scholar
  19. 19.
    Kamp, H.: A theory of truth and semantic representation. In: Groenendijk, J., Janssen, T., Stokhof, M. (eds.) Formal Methods in the Study of Language. Mathematical Centre, Amsterdam (1981)Google Scholar
  20. 20.
    Presutti, V., Draicchio, F., Gangemi, A.: Knowledge extraction based on discourse representation theory and linguistic frames. In: Teije, A., et al. (eds.) EKAW 2012. LNCS, vol. 7603, pp. 114–129. Springer, Heidelberg (2012). doi:10.1007/978-3-642-33876-2_12. http://wit.istc.cnr.it/stlab-tools/fred/ CrossRefGoogle Scholar
  21. 21.
    Bos, J.: Wide-coverage semantic analysis with boxer. In: Bos, J., Delmonte, R. (eds.) Semantics in Text Processing (STEP), pp. 277–286. College Publications, London (2008)Google Scholar
  22. 22.
    Hobbs, J.R., Stickel, M.E., Appelt, D.E., Martin, P.A.: Interpretation as abduction. Artif. Intell. 63(1–2), 69–142 (1993)CrossRefGoogle Scholar
  23. 23.
    Cai, S., Knight, K.: Smatch: an evaluation metric for semantic feature structures. In: Proceedings 51st Annual Meeting of the Association for Computational Linguistics, vol. 2, Short Papers, Sofia, Bulgaria, pp. 748–752 (2013)Google Scholar
  24. 24.
    Pust, M., Hermjakob, U., Knight, K., Marcu, D., May, J.: Parsing English into abstract meaning representation using syntax-based machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, Lisbon, Portugal, pp. 1143–1154. Association for Computational Linguistics, September 2015Google Scholar
  25. 25.
    Garg, S., Galstyan, A., Hermjakob, U., Marcu, D.: Extracting biomolecular interactions using semantic parsing of biomedical text. In: Proceedings of AAAI (2016)Google Scholar
  26. 26.
    Pan, X., Cassidy, T., Hermjakob, U., Ji, H., Knight, K.: Unsupervised entity linking with abstract meaning representation. In: Proceedings of North American Chapter Association for Computational Linguistics, Denver, Colorado, pp. 1130–1139 (2015)Google Scholar
  27. 27.
    Ashish, N., Dewan, P., Ambite, J.-L., Toga, A.W.: GEM: the GAAIN entity mapper. In: Ashish, N., Ambite, J.-L. (eds.) DILS 2015. LNCS, vol. 9162, pp. 13–27. Springer, Heidelberg (2015). doi:10.1007/978-3-319-21843-4_2 CrossRefGoogle Scholar
  28. 28.
    Parundekar, R., Knoblock, C.A., Ambite, J.L.: Discovering concept coverings in ontologies of linked data sources. In: Cudré-Mauroux, P., et al. (eds.) ISWC 2012. LNCS, vol. 7649, pp. 427–443. Springer, Heidelberg (2012). doi:10.1007/978-3-642-35176-1_27 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Gully A. Burns
    • 1
  • Ulf Hermjakob
    • 1
  • José Luis Ambite
    • 1
  1. 1.Information Sciences InstituteUniversity of Southern CaliforniaMarina del ReyUSA

Personalised recommendations