Abstract
We compare the contributions made by sequences of part of speech tags and sequences of phrase labels for the task of grammatical relation finding. Both are used for grammar induction, and we show that English labels of grammatical relations follow a very strict sequential order, but not as strict as POS tags, resulting in better performance of the latter on the relation finding task.
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
Collins, M.: Three generative, lexicalized models for statistical parsing. In: Proc. 35th ACL (1997)
Eisner, J.: Three new probabilistic models for dependency parsing: An exploration. In: Proc. COLING 1996 (1996)
Infante-Lopez, G., de Rijke, M.: Alternative approaches for generating bodies of grammar rules. In: Proc. 42nd ACL (2004)
Collins, M.: Head-Driven Statistical Models for Natural Language Parsing. PhD thesis, University of Pennsylvania, PA (1999)
Charniak, E.: Tree-bank Grammars. In: Proceedings AAAI 1996, Portland, Oregon (1996)
Infante-Lopez, G.: Two-Level Probabilistic Grammars for Natural Language Parsing. PhD thesis, Universiteit van Amsterdam (2005)
Buchholz, S.: Memory-Based Grammatical Relation Finding. PhD thesis, Universiteit van Tilburg (2002)
Abney, S., McAllester, D., Pereira, F.: Relating probabilistic grammars and automata. In: Proc. 37th ACL, pp. 542–549 (1999)
Manning, C., Schütze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge (1999)
Thollard, F., Dupont, P., de la Higuera, C.: Probabilistic DFA inference using Kullback-Leibler divergence and minimality. In: Proc. ICML, Stanford (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Infante-Lopez, G., de Rijke, M. (2006). Sequences of Part of Speech Tags vs. Sequences of Phrase Labels: How Do They Help in Parsing?. In: Gelbukh, A. (eds) Computational Linguistics and Intelligent Text Processing. CICLing 2006. Lecture Notes in Computer Science, vol 3878. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11671299_20
Download citation
DOI: https://doi.org/10.1007/11671299_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-32205-4
Online ISBN: 978-3-540-32206-1
eBook Packages: Computer ScienceComputer Science (R0)