Abstract
Much is still unknown about how children learn language, but it is clear that they perform “grounded” language learning: they learn the grammar and vocabulary not just from examples of sentences, but from examples of sentences in a particular context. Grounded language learning has been the subject of much research. Most of this work focuses on particular aspects, such as constructing semantic parsers, or on particular types of applications. In this paper, we take a broader view that includes an aspect that has received little attention until now: learning the meaning of phrases from phrase/context pairs in which the phrase’s meaning is not explicitly represented. We propose a simple model for this task that uses first-order logic representations for contexts and meanings, including a simple incremental learning algorithm. We experimentally demonstrate that the proposed model can explain the gradual learning of simple concepts and language structure, and that it can easily be used for interpretation, generation, and translation of phrases.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
This is in line with the work by Mooney et al. and with Wittgenstein’s views on the meaning of language.
- 2.
With a model learned from 2000 examples, the incorrect phrase “driehoek rode driehoek” was produced; this is a consequence of the belief that “het” is a shape, and the construction of a rule for shape color shape as a consequence.
References
Angluin, D., Becerra-Bonache, L.: A model of semantics and corrections in language learning. Technical report YALE/DCS/TR1425, Yale University (2010)
Angluin, D., Becerra-Bonache, L.: Effects of meaning-preserving corrections on language learning. In: CoNLL, pp. 97–105 (2011)
Chen, D.L., Kim, J., Mooney, R.J.: Training a multilingual sportscaster: Using perceptual context to learn language. JAIR 37, 397–435 (2010)
Chen, D.L., Mooney, R.J.: Learning to sportscast: a test of grounded language acquisition. In: ICML, pp. 128–135 (2008)
Harnad, S.: Symbol grounding problem. Scholarpedia 2(7), 2373 (2007)
de la Higuera, C.: Grammatical Inference, Learning Automata and Grammars. Cambridge University Press, New York (2010)
Feldman, J., Lakoff, G., Stolcke, A., Weber, S.: Miniature language acquisition: A touchstone for cognitive science. In: CogSci, pp. 686–693 (1994)
Jones, B., Andreas, J., Bauer, D., Hermann, K.M., Knight, K.: Semantics-based machine translation with hyperedge replacement grammars. In: COLING 2012, pp. 1359–1376 (2012)
Kate, R.J., Mooney, R.J.: Learning language semantics from ambiguous supervision. In: AAAI, pp. 895–900 (2007)
Kietz, J.U.: A comparative study of structural most specific generalizations used in machine learning. In: Third International Workshop on Inductive Logic Programming, pp. 149–164 (1993)
Kim, J., Mooney, R.J.: Generative alignment and semantic parsing for learning from ambiguous supervision. In: COLING, pp. 543–551 (2010)
Krahmer, E., van Deemter, K.: Computational generation of referring expressions: A survey. Comput. Linguist. 38(1), 173–218 (2012)
Kwiatkowski, T., Goldwater, S., Zettlemoyer, L.S., Steedman, M.: A probabilistic model of syntactic and semantic acquisition from child-directed utterances and their meanings. In: EACL, pp. 234–244 (2012)
Lloyd, J.W.: Foundations of Logic Programming, 2nd edn. Springer, Berlin (1987)
Lu, W., Ng, H.T., Lee, W.S., Zettlemoyer, L.S.: A generative model for parsing natural language to meaning representations. In: EMNLP, pp. 783–792 (2008)
Muggleton, S., Raedt, L.D.: Inductive logic programming: Theory and methods. J. Logic Program. 19(20), 629–679 (1994)
Plotkin, G.D.: A note on inductive generalization. In: Melter, B., Michie, D. (eds.) Machine Intelligence 5, pp. 153–163. Edinburgh University Press, Edinburgh (1970)
Pust, M., Hermjakob, U., Knight, K., Marcu, D., May, J.: Using syntax-based machine translation to parse english into abstract meaning representation, CoRR abs/1504.06665 (2015)
Siskind, J.: A computational study of cross-situational techniques for learning word-to-meaning mappings. Cognition 61, 39–61 (1996)
Wong, Y.W., Mooney, R.J.: Learning synchronous grammars for semantic parsing with lambda calculus. In: ACL, pp. 960–967 (2007)
Zettlemoyer, L.S., Collins, M.: Learning context-dependent mappings from sentences to logical form. In: ACL, pp. 976–984 (2009)
Acknowledgements
Part of this work was done while HB was visiting Laboratoire Hubert Curien.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Becerra-Bonache, L., Blockeel, H., Galván, M., Jacquenet, F. (2015). A First-Order-Logic Based Model for Grounded Language Learning. In: Fromont, E., De Bie, T., van Leeuwen, M. (eds) Advances in Intelligent Data Analysis XIV. IDA 2015. Lecture Notes in Computer Science(), vol 9385. Springer, Cham. https://doi.org/10.1007/978-3-319-24465-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-24465-5_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24464-8
Online ISBN: 978-3-319-24465-5
eBook Packages: Computer ScienceComputer Science (R0)