Abstract
Constraint satisfaction has been central to the ICSI/UC Berkeley Neural Theory of Language (NTL) project, but this aspect has not previously been emphasized. The ECG Analysis program combines constraints from several aspects of the formalism: deep semantic schemas, embodied constructions and ontological knowledge. In this chapter we focus on some applications of deep semantic constraints that extend the Embodied Construction Grammar formalism (ECG) and Analyzer. The first example is a shallow reference resolution method that is based on the combination of the recency principle with syntactic and semantic compatibility between the anaphor and the referent. The method has been implemented and tested as part of a system capable of understanding Solitaire card-game instructions, with promising results. Similar deep ontology-driven constraint satisfaction techniques can be exploited to handle many cases of Noun-Noun compounds and metaphorical constructions. Implemented examples of these are also presented.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Prince, A., Smolensky, P.: Optimality Theory: Constraint interaction in generative grammar. Blackwell (2004)
Feldman, J.: From Molecule to Metaphor: A Neural Theory of Language. MIT Press (2006)
Kehler, A.: Coherence, reference and the theory of grammar. CSLI Publications, Stanford (2002)
Bryant, J.: Best-Fit constructional analysis. Ph.D. thesis. UC Berkeley. Berkeley, CA (2008)
Hobbs, J.: Pronoun resolution. Technical Report. CUNY (1976)
Hobbs, J.: Resolving pronoun references. Lingua 44, 311–338 (1978)
Asher, N., Lascarides, A.: Logics of conversation. Cambridge University Press, Cambridge (2003)
Lappin, S., Leass, H.: An algorithm for pronominal anaphora resolution. Computational Linguistics 4, 535–561 (1994)
Mitkov, R.: Robust pronoun resolution with limited knowledge. In: Proc. COLIN/ACL 1998, pp. 869–875 (1998)
Soon, W., Ng, H., Lim, D.: A machine learning approach to coreference resolution of noun phrases. Computational Linguistics 4, 521–544 (2001)
Ponzetto, S., Strube, M.: Exploiting semantic role labeling, wordnet and wikipedia for coreference resolution. In: Proceedings of the HLT 2006, New York City, pp. 192–199 (2006)
Ng, V., Cardie, C.: Improving machine learning approaches to coreference resolution. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 104–111 (2002)
Ng, V.: Semantic class induction and coreference resolution. In: Proceedings of the 45th Annual Meeting of the Association for Computational Linguistics, ACL 2007 (2007)
Bryant, J., Gilardi, L.: A cognitive model of sentence interpretation. In: Boas, H.C. (ed.) Computational Approaches to Embodied Construction Grammar, John Benjamins, San Diego (2013)
Feldman, J., Dodge, E., Bryant, J.: Embodied construction grammar. In: Heine, B., Heiko, N. (eds.) The Oxford Handbook of Linguistic Analysis, pp. 111–138. Oxford University Press, Oxford (2010)
Narayanan, S.: KARMA: Knowledge-based action representations for metaphor and aspect. Ph.D. thesis. UC Berkeley. Berkeley, CA (1997)
Chang, N., Mok, E.: A structured context model for grammar learning. In: Proceedings of the 2006 International Joint Conference on Neural Networks, Vancouver, BC (2006)
Mok, E.: Contextual bootstrapping for grammar learning. Ph.D. thesis. UC Berkeley. Berkeley, CA (2009)
Poon, H., Domingos, P.: Joint unsupervised coreference resolution with markov logic. In: Proceedings of the 2008 Conference on Empirical Methods in Natural Language Processing, EMNLP, Honolulu, Hawaii, pp. 650–659 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Oliva, J., Feldman, J., Gilardi, L., Dodge, E. (2013). Ontology Driven Contextual Best Fit in Embodied Construction Grammar. In: Duchier, D., Parmentier, Y. (eds) Constraint Solving and Language Processing. CSLP 2012. Lecture Notes in Computer Science, vol 8114. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41578-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-41578-4_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41577-7
Online ISBN: 978-3-642-41578-4
eBook Packages: Computer ScienceComputer Science (R0)