Abstract
In this paper we propose an unsupervised strategy for learning syntactic information that proceeds in several steps. First, we identify, cluster, and classify function words from unannotated corpora. Then, the acquired information is used in two different learning processes. On the one hand, it is used to learn morpho-syntactic categories of nouns and, on the other, it turns out to be useful to also induce syntactic/semantic relationships between content words. Experiments performed on Portuguese and English corpora are reported.
Research supported by Program POSI, FCT/MCT, Portugal; ref: SFRH/BPD/ 11189/2002
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 subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Clark, A.: Inducing syntactic categories by context distribution clustering. In: Proceedings of CoNLL-2000, pp. 91–94 (2000)
Finch, S., Chater, N.: Bootstrapping syntactic categories. In: 14th Annual Meeting of the Cogntive Science Society, pp. 820–825 (1992)
Gamallo, P., Agustini, A., Lopes, G.P.: Learning subcategorisation information to model a grammar with co-restrictions. Traitement Automatique de la Langue 44(1), 93–117 (2003)
Grefenstette, G.: Explorations in Automatic Thesaurus Discovery. Kluwer Academic Publishers, USA (1994)
Hughes, J., Atwell, E.: The automated evaluation of inferred word classifications. In: Proceedings of ECAI 1994: 11th European Conference on Artificial Intelligence, pp. 535–540 (1994)
Pustejovsky, J.: The Generative Lexicon. MIT Press, Cambridge (1995)
Redington, M., Chater, N., Finch, S.: Distributional information adn the acquisition of linguistic categories: A statistical approach. In: 15th Anual Conference of the Cognitive Science Society, pp. 848–853. Erlbaum, Hillsdale (1993)
Schutze, H.: Part-of-speech induction from scratch. In: ACL 1993, Ohio State (1993)
Smith, T.C., Witten, I.H.: Probability-driven lexical classification: A corpus-based approach. In: PACLING 1995 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Gamallo, P., Lopes, G.P., Da Silva, J.F. (2004). A Divide-and-Conquer Approach to Acquire Syntactic Categories. In: Paliouras, G., Sakakibara, Y. (eds) Grammatical Inference: Algorithms and Applications. ICGI 2004. Lecture Notes in Computer Science(), vol 3264. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30195-0_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-30195-0_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23410-4
Online ISBN: 978-3-540-30195-0
eBook Packages: Springer Book Archive