Abstract
According to Cognitive Grammar (CG) theory, the overall structure of a natural language is motivated by a relatively small set of domain-independent cognitive abilities. In this paper, we draw insights from CG to propose an approach to natural language parsing with little syntactic annotation. A sentence functions as a cohesive whole because its parts are meaningfully linked. We propose that every part of a sentence can be analysed along three axes: composition, interaction and autonomy. When two expressions semantically correspond in all the three axes we call them cohesive. We present an algorithm that reads parts of sentences incrementally, recognises their construction schemas along the three axes, assembles any two component schemas into one composite schema if they are cohesive, parses a span of text as incrementally successive assembly of components into composites, retains multiple running parses within the span and chooses the best parse. The basic construction schema definitions and their patterns of assembly are implemented as dictionary-cum-rules because they are fewer in number, largely language-independent and can be extended to handle language-specific variations. A basic feedforward neural network component was trained to learn all valid patterns of assemblies possible in a span of text and to choose the best parse. A successful parse exhausts all the words in the sentence and ensures local cohesion and assembly at every stage of analysis. We present our approach, parser implementation and evaluation results in Welsh and English. By adding WordNet synsets we are able to show improvements in parser performance.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Conventions of image schema used in CG are more detailed and specific than what is used here. The figures used here do not share those conventions. This is just our own rough sketch for the sake of illustration. Conventions used: circle - THING, rectangle - RELATIONSHIP, rectangle with right side curved - any RELATIONSHIP which anticipates a THING, double arrow - assembly of two entities, dotted - unknown entity waiting elaboration, colour-filled - focussed entity, colour border - portions scanned for construing along an axis.
References
Chomsky, N., Lightfoot, D.W.: Syntactic Structures. Walter de Gruyter, Berlin (2002)
Di Caro, L., Grella, M.: Sentiment analysis via dependency parsing. Comput. Stand. Interfaces 35(5), 442–453 (2013)
Ellis, N.C., O’Dochartaigh, C., Hicks, W., Morgan, M., Laporte, N.: Cronfa electroneg o gymraeg (CEG): a 1 million word lexical database and frequency count for welsh (2001). http://corpws.cymru/ceg
Eriguchi, A., Tsuruoka, Y., Cho, K.: Learning to parse and translate improves neural machine translation. arXiv preprint arXiv:1702.03525 (2017)
Frank, S.L., Bod, R., Christiansen, M.H.: How hierarchical is language use? Proc. R. Soc. B Biol. Sci. 279(1747), 4522–4531 (2012)
Goldberg, A.E.: Constructions at Work: The Nature of Generalization in Language. Oxford University Press, Oxford (2006)
Kaiser, E., Trueswell, J.C.: The role of discourse context in the processing of a flexible word-order language. Cognition 94(2), 113–147 (2004)
Klein, D., Manning, C.D.: Corpus-based induction of syntactic structure: models of dependency and constituency. In: Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics, p. 478. Association for Computational Linguistics (2004)
Langacker, R.W., Langacker, R.: Cognitive Grammar: A Basic Introduction. OUP, Oxford (2008)
Lapata, M.: Probabilistic text structuring: experiments with sentence ordering. In: Proceedings of the 41st Annual Meeting on Association for Computational Linguistics-Volume 1, pp. 545–552. Association for Computational Linguistics (2003)
Lerdahl, F., Jackendoff, R.S.: A Generative Theory of Tonal Music. MIT Press, Cambridge (1996)
Li, C., Liu, Y., Liu, F., Zhao, L., Weng, F.: Improving multi-documents summarization by sentence compression based on expanded constituent parse trees. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 691–701 (2014)
Müller, S.: Grammatical Theory: From Transformational Grammar to Constraint-Based Approaches. Language Science Press, Berlin (2019)
Muralidaran, V., Misra Sharma, D.: Construction grammar based annotation framework for parsing Tamil. In: Gelbukh, A. (ed.) CICLing 2016. LNCS, vol. 9623, pp. 378–396. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-75477-2_27
Neubig, G., et al.: DyNet: the dynamic neural network toolkit. arXiv preprint arXiv:1701.03980 (2017)
Ohta, T., et al.: An intelligent search engine and GUI-based efficient MEDLINE search tool based on deep syntactic parsing. In: Proceedings of the COLING/ACL 2006 Interactive Presentation Sessions, pp. 17–20 (2006)
Paul, D.B., Baker, J.M.: The design for the wall street journal-based CSR corpus. In: Proceedings of the Workshop on Speech and Natural Language, pp. 357–362. Association for Computational Linguistics (1992)
Saffran, J.R.: The use of predictive dependencies in language learning. J. Mem. Lang. 44(4), 493–515 (2001)
Vigneshwaran, M.: Construction grammar approach for Tamil dependency parsing. Ph.D. thesis, International Institute of Information Technology Hyderabad (2016)
Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity in phrase-level sentiment analysis. In: Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pp. 347–354 (2005)
Yu, J., Chen, W., Li, Z., Zhang, M.: Building powerful dependency parsers for resource-poor languages. In: Lin, C.-Y., Xue, N., Zhao, D., Huang, X., Feng, Y. (eds.) ICCPOL/NLPCC -2016. LNCS (LNAI), vol. 10102, pp. 27–38. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-50496-4_3
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Muralidaran, V., Spasić, I., Knight, D. (2020). A Cognitive Approach to Parsing with Neural Networks. In: Espinosa-Anke, L., Martín-Vide, C., Spasić, I. (eds) Statistical Language and Speech Processing. SLSP 2020. Lecture Notes in Computer Science(), vol 12379. Springer, Cham. https://doi.org/10.1007/978-3-030-59430-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-59430-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59429-9
Online ISBN: 978-3-030-59430-5
eBook Packages: Computer ScienceComputer Science (R0)