Experiments with Learning Parsing Heuristics
Pages 307 - 313
Abstract
Any large language processing software relies in its operation on heuristic decisions concerning the strategy of processing. These decisions are usually "hard-wired" into the software in the form of hand-crafted heuristic rules, independent of the nature of the processed texts. We propose an alternative, adaptive approach in which machine learning techniques learn the rules from examples of sentences in each class. We have experimented with a variety of learning techniques on a representative instance of this problem within the realm of parsing. Our approach lead to the discovery of new heuristics that perform significantly better than the current hand-crafted heuristic. We discuss the entire cycle of application of machine learning and suggest a methodology for the use of machine learning as a technique for the adaptive optimisation of language-processing software.
References
[1]
Atkinson, H. F. (1990) Mechanics of Small Engines. New York: Gregg Division, McGraw-Hill.
[2]
Brill E. (1993) "Automatic Grammar Induction and Parsing Free Text: A Transformation-Based Approach", Proc. of the 31st Annual Meeting of the ACL, pp. 259--265.
[3]
Buo F. D. (1996) "FeasPar---A Feature Structure Parser Learning to Parse Spontaneous Speech", Ph.D. Thesis, Fakultät für Informatik, Univ. Karlsruhe, Germany.
[4]
Delisle S. (1994) "Text Processing without a priori Domain Knowledge: Semi-Automatic Linguistic for Incremental Knowldge Acquisition", Ph.D. Thesis, Dept. of Computer Science, Univ. of Ottawa. Published as technical report TR-94-02.
[5]
Ezawa K., Singh M. & Norton S. (1996) "Learning Goal Oriented Bayesian Networks for Telecommunications Risk Management", Proc. of the 13th International Conf. on Machine Learning, pp. 139--147.
[6]
Famili A. & Turney P. (1991) "Intelligently Helping the Human Planner in Industrial Process Planing", AI EDAMAI for Engineering Design Analysis and Manufacturing, 5(2), pp. 109--124.
[7]
Hermjakob U. & Mooney R. J. (1997) "Learning Parse and Translation Decisions From Examples With Rich Context", Proc. of ACL-EACL Conf., pp. 482--489.
[8]
Huyck C. R. & Lytinen S. L. (1993) "Efficient Heuristic Natural Language Parsing", Proc. of the 11th National Conf. on AI, pp. 386--391.
[9]
Johnson R. A. & Wichern D. W. (1992) Applied Multivariate Statistical Analysis, Prentice Hall.
[10]
Kohavi R., John G., Long R., Manley D. & Pleger K. (1994) "MLC++: A machine learning library in C++", Tools with AI, IEEE Computer Society Press, pp. 740--743.
[11]
Lawrence S., Fong S. & Lee Giles C. (1996) "Natural Language Grammatical Inference: A Comparison of Recurrent Neural Networks and Machine Learning Methods", in S. Wermter, E. Riloff and G. Scheler (eds.), Symbolic, Connectionnist, and Statistical Approaches to Learning for Natural Language Processing, Lectures Notes in AI, Springer-Verlag, pp. 33--47.
[12]
Litman D. (1996) "Cue Phrase Classification Using Machine Learning", Journal of AI Research, 5, pp. 53--95.
[13]
Magerman D. (1995) "Statistical Decision-Tree Models for Parsing", Proc. of the 33rd Annual Meeting of the ACL, 276--283.
[14]
McCarthy J. & Lehnert W. G. (1995) "Using Decision Trees for Coreference Resolution", Proc. of IJCAI-95, pp. 1050--1055.
[15]
Neumann G. (1997) "Applying Explanation-based Learning to Control and Speeding-up Natural Language Generation", Proc. of ACL-EACL Conf., pp. 214--221.
[16]
Quinlan J. R. (1993) C4.5: Programs for Machine Learning, Morgan Kaufmann.
[17]
Quirk R., Greenbaum S., Leech G. & Svartvik J. (1985) A Comprehensive Grammar of the English Language, Longman.
[18]
Samuelsson C. (1994) "Grammar Specialization Through Entropy Thresholds", Proc. of the 32nd Annual Meeting of the ACL, pp. 188--195.
[19]
Simmons F. S. & Yu Y. H. (1992) "The Acquisition and Use of Context-dependent Grammars for English", Computational Linguistics, 18(4), pp. 392--418.
[20]
Soderland S. G. (1997) "Learning Text Analysis Rules for Domain-Specific Natural Language Processing", Ph.D. Thesis, Dept. of Computer Science, Univ. of Massachusetts.
[21]
Theeramunkong T., Kawaguchi Y. & Okumura (1997) "Exploiting Contextual Information in Hypothesis Selection for Grammar Refinement", Proc. of the CEGDLE Workshop at ACL-EACL'97, pp.78-83.
[22]
Wnek J. & Michalski R.S. (1994) "Hypothesis-driven constructive induction in AQ17-HCI: a method and experiments", Machine Learning, 14(2), pp. 139-168.
[23]
Zelle J.M. & Mooney R.J. (1994) "Inducing Deterministic Prolog Parsers from Treebanks: A Machine Learning Approach", Proc. of the 12th National Conf. on AI, pp.748-753.
- Experiments with Learning Parsing Heuristics
Recommendations
LLLR parsing
SAC '13: Proceedings of the 28th Annual ACM Symposium on Applied ComputingThe idea of an LLLR parsing is presented. An LLLR(k) parser can be constructed for any LR(k) grammar but it produces the left parse of the input string in linear time (in respect to the length of the derivation) without backtracking. If used as a basis ...
Heuristics for broad-coverage natural language parsing
HLT '93: Proceedings of the workshop on Human Language TechnologyThe Slot Grammar system is interesting for natural language applications because it can deliver parses with deep grammatical information on a reasonably broad scale. The paper describes a numerical scoring system used in Slot Grammar for ambiguity ...
Comments
Information & Contributors
Information
Published In
Sponsors
- Government of Canada
- Université de Montréal
Publisher
Association for Computational Linguistics
United States
Publication History
Published: 10 August 1998
Qualifiers
- Article
Acceptance Rates
Overall Acceptance Rate 85 of 443 submissions, 19%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 311Total Downloads
- Downloads (Last 12 months)28
- Downloads (Last 6 weeks)5
Reflects downloads up to 11 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in