Abstract
In a previous work, a new probabilistic context-free grammar (PCFG) model for natural language parsing derived from a tree bank corpus has been introduced. The model estimates the probabilities according to a generalized k-grammar scheme for trees. It allows for faster parsing, decreases considerably the perplexity of the test samples and tends to give more structured and refined parses. However, it suffers from the problem of incomplete coverage. In this paper, we compare several smoothing techniques such as backing-off or interpolation that are used to avoid assigning zero probability to any sentence.
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
Charniak, E., Carroll, G.: Context-sensitive statistics for improved grammatical language models. In: Proceedings of the 12th National Conference on Artificial Inteligence, Seattle, WA, pp. 742–747. AAAI Press, Menlo Park (1994)
Johnson, M.: PCFG models of linguistic tree representations. Computational Linguistics 24(4), 613–632 (1998)
Verdú-Mas, J.L., Forcada, M.L., Carrasco, R.C., Calera-Rubio, J.: Tree k-grammar models for natural language modelling and parsing. In: Caelli, T.M., Amin, A., Duin, R.P.W., Kamel, M.S., de Ridder, D. (eds.) SPR 2002 and SSPR 2002. LNCS, vol. 2396, pp. 56–63. Springer, Heidelberg (2002)
Charniak, E.: Treebank grammars. In: Proceedings of the Thirteenth National Conference on Artificial Intelligence, pp. 1031–1036. AAAI Press/MIT Press (1996)
Brown, P.F., Della Pietra, V.J., deSouza, P.V., Lai, J.C., Mercer, R.L.: Class-based n-gram models of natural language. Computational Linguistics 18(4), 467–479 (1992)
Chen, S.F., Goodman, J.: An empirical study of smoothing techniques for language modeling. In: Joshi, A., Palmer, M. (eds.) Proceedings of the Thirty-Fourth Annual Meeting of the Association for Computational Linguistics, San Francisco, pp. 310–318. Morgan Kaufmann Publishers, San Francisco (1996)
Marcus, M.P., Santorini, B., Marcinkiewicz, M.A.: Building a large annotated corpus of english: the penn treebank. Computational Linguistics 19, 313–330 (1993)
Nivat, M., Podelski, A.: Minimal ascending and descending tree automata. SIAM Journal on Computing 26(1), 39–58 (1997)
Bahl, L.R., Brown, P.F., de Souza, P.V., Mercer, R.L.: A tree-based statistical language model for natural language speech recognition. In: Waibel, A., Lee, K.F. (eds.) Readings in Speech Recognition, pp. 507–514. Kaufmann, San Mateo (1990)
Stolcke, A.: An efficient probabilistic context-free parsing algorithm that computes prefix probabilities. In: Computational Linguistics, MIT Press for the Association for Computational Linguistics, vol. 21 (1995)
Black, E., Abney, S., Flickinger, D., Gdaniec, C., Grishman, R., Harrison, P., Hindle, D., Ingria, R., Jelinek, F., Klavans, J., Liberman, M., Marcus, M., Roukos, S., Santorini, B., Strzalkowski, T.: A procedure for quantitatively comparing the syntatic coverage of english grammars. In: Proc. Speech and Natural Language Workshop 1991, San Mateo, CA, pp. 306–311. Morgan Kauffmann, San Francisco (1991)
Manning, C.D., Schutze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Verdú-Mas, J.L., Calera-Rubio, J., Carrasco, R.C. (2003). Smoothing Techniques for Tree-k-Grammar-Based Natural Language Modeling. In: Perales, F.J., Campilho, A.J.C., de la Blanca, N.P., Sanfeliu, A. (eds) Pattern Recognition and Image Analysis. IbPRIA 2003. Lecture Notes in Computer Science, vol 2652. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-44871-6_122
Download citation
DOI: https://doi.org/10.1007/978-3-540-44871-6_122
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40217-6
Online ISBN: 978-3-540-44871-6
eBook Packages: Springer Book Archive