Prepositional Phrase Attachment Through a Backed-off Model

  • M. Collins
  • J. Brooks
Part of the Text, Speech and Language Technology book series (TLTB, volume 11)


Recent work has considered corpus-based or statistical approaches to the problem of prepositional phrase attachment ambiguity. Typically, ambiguous verb phrases of the form v np1 p np2 are resolved through a model which considers values of the four head words (v, n1, p and n2). This paper shows that the problem is analogous to n-gram language models in speech recognition, and that one of the most common methods for language modeling, the backed-off estimate, is applicable. Results on Wall Street Journal data of 84.5% accuracy are obtained using this method. A surprising result is the importance of low-count events — ignoring events which occur less than 5 times in training data reduces performance to 81.6%.


Wall Street Journal Head Noun Maximum Entropy Model Sparse Data Problem Head Word 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Brill, E. and Resnik, P. 1994. A Rule-Based Approach to Prepositional Phrase Attachment Disambiguation. Proceedings of the fifteenth international conference on computational linguistics, Kyoto, Japan.Google Scholar
  2. Gale, W. and Church, K. 1990. Poor Estimates of Context are Worse than None. Proceedings of the June 1990 DARPA Speech and Natural Language Workshop, Hidden Valley, Pennsylvania.Google Scholar
  3. Karp, D., Schabes, Y., Zaidel, M. and Egedi, D. 1994. A Freely Available Wide Coverage Morphological Analyzer for English. Proceedings of the fifteenth International Conference on Computational Linguistics, Kyoto, Japan.Google Scholar
  4. Hindle, D. and Rooth, M. 1993 Structural Ambiguity and Lexical Relations. Com putational Linguistics, 19 (1): 103–120.Google Scholar
  5. Katz, S. 1987. Estimation of Probabilities from Sparse Data for the Language Model Component of a Speech Recogniser, IEEE Transactions on Acoustics, Speech, and Signal Processing Vol. ASSP-35, No. 3, 1987.Google Scholar
  6. Marcus, M., Santorini, B. and Marcinkiewicz, M. 1993. Building a Large Annotated Corpus of English: the Penn Treebank. Computational Linguistics, 19 (2): 313–330.Google Scholar
  7. Ratnaparkhi, A., Reynar, J. and Roukos, S. 1994. A Maximum Entropy Model for Prepositional Phrase Attachment. Proceedings of the ARPA Workshop on Human Language Technology, Plainsboro, NJ, March 1994.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1999

Authors and Affiliations

  • M. Collins
  • J. Brooks

There are no affiliations available

Personalised recommendations