Hostname: page-component-78c5997874-v9fdk Total loading time: 0 Render date: 2024-11-03T08:42:24.041Z Has data issue: false hasContentIssue false
  • English
  • Français

A statistical model for grammar mapping

Published online by Cambridge University Press:  20 February 2015

A. BASIRAT ,
H. FAILI  and
J. NIVRE
A. BASIRAT
Affiliation:
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran email: [email protected] Department of Linguistics and Philology, Uppsala University, Uppsala, Sweden email: [email protected]
H. FAILI
Affiliation:
School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, Iran email: [email protected] School of Computer Science, Institute for Research in Fundamental Sciences (IPM), P. O. Box 19395-5746, Tehran, Iran email: [email protected]
J. NIVRE
Affiliation:
Department of Linguistics and Philology, Uppsala University, Uppsala, Sweden email: [email protected]
Get access Rights & Permissions [Opens in a new window]

Abstract

The two main classes of grammars are (a) hand-crafted grammars, which are developed by language experts, and (b) data-driven grammars, which are extracted from annotated corpora. This paper introduces a statistical method for mapping the elementary structures of a data-driven grammar onto the elementary structures of a hand-crafted grammar in order to combine their advantages. The idea is employed in the context of Lexicalized Tree-Adjoining Grammars (LTAG) and tested on two LTAGs of English: the hand-crafted LTAG developed in the XTAG project, and the data-driven LTAG, which is automatically extracted from the Penn Treebank and used by the MICA parser. We propose a statistical model for mapping any elementary tree sequence of the MICA grammar onto a proper elementary tree sequence of the XTAG grammar. The model has been tested on three subsets of the WSJ corpus that have average lengths of 10, 16, and 18 words, respectively. The experimental results show that full-parse trees with average F1-scores of 72.49, 64.80, and 62.30 points could be built from 94.97%, 96.01%, and 90.25% of the XTAG elementary tree sequences assigned to the subsets, respectively. Moreover, by reducing the amount of syntactic lexical ambiguity of sentences, the proposed model significantly improves the efficiency of parsing in the XTAG system.

Type
Articles
Information
Natural Language Engineering , Volume 22 , Issue 2 , March 2016 , pp. 215 - 255
Copyright
Copyright © Cambridge University Press 2015 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Abeillé, A., Clément, L., and Toussenel, F. 2003. Building a treebank for French. In Abeill, A. (ed.), Treebanks, pp. 165–187. Text, Speech and Language Technology, vol. 20. Netherlands: Springer.CrossRefGoogle Scholar
Abney, S., Flickenger, S., Gdaniec, C., Grishman, C., Harrison, P., Hindle, D., Ingria, R., Jelinek, F., Klavans, J., Liberman, M., Marcus, M., Roukos, S., Santorini, B., & Strzalkowski, T. 1991. Procedure for quantitatively comparing the syntactic coverage of English grammars. In Proceedings of the Workshop on Speech and Natural Language, ACL 1991, Association for Computational Linguistics. California, USA, pp. 306–311Google Scholar
Bangalore, S., and Joshi, A., 1999. Supertagging: an approach to almost parsing. Computational Linguistics 25 (2): 237–266.Google Scholar
Bangalore, S., Doran, C., Hockey, B., and Joshi, A. 1996 (August). An approach to robust partial parsing and evaluation metrics. In Proceedings of the 8th European Summer School In Logic, Language and Information, Prague, The Czech Republic, pp. 70–82Google Scholar
Bangalore, S., Haffner, P., and Emami, G. 2005. Factoring global inference by enriching local representations. Technical Report, AT&T Labs - Research.Google Scholar
Bangalore, S., Boulllier, P., Nasr, A., Rambow, O., and Sagot, B. 2009. MICA: a probabilistic dependency parser based on tree insertion grammars. In Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers, NAACL-Short 2009. Association for Computational Linguistics. Boulder, Colorado, pp. 185–188Google Scholar
Basirat, A., and Faili, H., 2011. Constructing linguistically motivated structures from statistical grammars. In Proceedings of International Conference on Recent Advances in Natural Language Processing, RANLP 2011. Association for Computational Linguistics. Hissar, Bulgaria, pp. 63–96.Google Scholar
Basirat, A., and Faili, H., 2013. Bridge the gap between statistical and hand-crafted grammars. Computer Speech and Language 27 (5): 1085–1104.CrossRefGoogle Scholar
Baum, L. E., Petrie, T., Soules, G., and Weiss, N., 1970. A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains. The Annals of Mathematical Statistics 41 (1): 164–171.CrossRefGoogle Scholar
Bonfante, G., Guillaume, B., and Perrier, G., 2004. Polarization and abstraction of grammatical formalisms as methods for lexical disambiguation. In Proceedings of the 20th International Conference on Computational Linguistics, COLING 2004. Association for Computational Linguistics. Geneva, Switzerland, pp. 303–309.Google Scholar
Boullier, P., and Deschamp, P. 1988. Le systeme SYNTAX™ manuel d’utilisation et de mise en oeuvre sous UNIX™. http://syntax.gforge.inria.fr/syntax3.8-manual.pdf.Google Scholar
Chandrasekar, R., and Bangalore, S. 1997. Gleaning information from the web: using syntax to filter out irrelevant information. In Proceedings of AAAI Symposium on NLP for the World Wide Web, California, USA, pp. 27–34.Google Scholar
Chen, J. 2001. Toward efficient statistical parsing using lexicalized grammatical information, Ph.D. thesis, University of Delaware.Google Scholar
Chiang, D. 2000. Statistical parsing with an automatically-extracted tree adjoining grammar. In Proceedings of the 38th Annual Meeting on Association for Computational Linguistics, ACL 2000. Association for Computational Linguistics. Hong Kong, pp. 456–463Google Scholar
Chiang, D., and Rambow, O., 2006. The hidden TAG model: synchronous grammars for parsing resource-poor languages. In Proceedings of the Eighth International Workshop on Tree Adjoining Grammar and Related Formalisms, Association for Computational Linguistics. Sydney, Australia, pp. 1–8.Google Scholar
Chomsky, N., 1959. On certain formal properties of grammars. Information and control 2 (2): 137–167.CrossRefGoogle Scholar
Dang, H. T., Kipper, K., and Palmer, M. 2000. Integrating compositional semantics into a verb lexicon. In Proceedings of the 18th Conference on Computational Linguistics, COLING 2000, Association for Computational Linguistics. Saarbrücken, Germany. vol. 2, pp. 1011–1015CrossRefGoogle Scholar
DeNeefe, S., and Knight, K., 2009. Synchronous tree adjoining machine translation. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, EMNLP 2009, Association for Computational Linguistics. Singapore. vol. 2, pp. 727–736.CrossRefGoogle Scholar
Eddy, B., Bental, D., and Cawsey, A., 2001. An algorithm for efficiently generating summary paragraphs using tree-adjoining grammar. In Proceedings of the 8th European workshop on Natural Language Generation, EWNLG 2001, Association for Computational Linguistics. Toulouse, France. vol. 8, pp. 1–8.CrossRefGoogle Scholar
Forbes, K., Miltsakaki, E., Prasad, R., Sarkar, A., Joshi, A. K., and Webber, B., 2003. D-LTAG system: discourse parsing with a lexicalized tree-adjoining grammar. Journal of Logic, Language and Information 12 (3): 261–279.CrossRefGoogle Scholar
Frank, R. 2004. Phrase Structure Composition and Syntactic Dependencies, vol. 38, The MIT Press.Google Scholar
Gardent, C., and Kallmeyer, L., 2003. Semantic construction in Feature-based TAG. In Proceedings of the 10th Conference on European Chapter of the Association for Computational Linguistics, EACL 2003, Association for Computational Linguistics. Budapest, Hungary. vol. 1, pp. 123–130.Google Scholar
Goodman, J., 1996. Parsing algorithms and metrics. In Proceedings of the 34th annual meeting on Association for Computational Linguistics, ACL 1996. Association for Computational Linguistics. California, USA, pp. 177–183.CrossRefGoogle Scholar
Han, C., Han, N., Ko, E., and Palmer, M., 2002. Development and evaluation of a Korean treebank and its application to NLP. In Proceedings of the 3rd International Conference on Language Resources and Evaluation, LREC 2002. European Language Resources Association (ELRA). Canary Islands, Spain, pp. 1635–1642.Google Scholar
Hemphill, C. T., Godfrey, J. J., and Doddington, G. R. 1990. The ATIS spoken language systems pilot corpus. In Proceedings of the Workshop on Speech and Natural Language. HLT 1990. Association for Computational Linguistics. Pennsylvania, USA, pp. 96–101.Google Scholar
Hernando, D., Crespi, V., and Cybenko, G., 2005. Efficient computation of the hidden Markov model entropy for a given observation sequence. Information Theory, IEEE Transactions 51 (7): 2681–2685.CrossRefGoogle Scholar
Johnson, M. 2007. Why doesn’t EM find good HMM POS-taggers? In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, EMNLP-CoNLL 2007. Association for Computational Linguistics. Prague, Czech Republic, pp. 296–305.Google Scholar
Joshi, A. K., and Schabes, Y. 1997. Tree-adjoining grammars. In Rozenberg, G. and Salomaa, A. (eds.) Handbook of formal languages, 69–123. Springer Berlin Heidelberg.CrossRefGoogle Scholar
Joshi, A. K., and Vijay-Shanker, K. 2001. Compositional semantics with lexicalized tree-adjoining grammar (LTAG): how much underspecification is necessary? In Bunt, H.et al. (eds.), Computing Meaning,. Springer Netherlands, vol. 77, pp. 147–163.Google Scholar
Joshi, A. K. 1985. Tree adjoining grammars: how much context-sensitivity is necessary for characterizing structural descriptions? In: Dowty, David R.et al. (eds.) Natural language parsing: Psychological, computational and theoretical perspectives, 206–250. Cambridge: Cambridge University Press.CrossRefGoogle Scholar
Kaeshammer, M. 2012. A German Treebank and Lexicon for Tree-Adjoining Grammars, Master thesis. Saarland University.Google Scholar
Kallmeyer, L., Lichte, T., Maier, W., Parmentier, Y., and Dellert, J., 2008. Developing a TT-MCTAG for German with an RCG-based parser. In Proceedings of the 6th International Conference on Language Resources and Evaluation, LREC 2008. European Language Resources Association (ELRA). Marrakech, Morocco, pp. 782–789.Google Scholar
Kaplan, R. M., and Bresnan, J. 1982. Lexical-functional grammar: a formal system for grammatical representation. The mental representation of grammatical relations, pp. 173–281, Cambridge, MA: MIT.Google Scholar
Kipper, K., Dang, H., and Palmer, M., 2000. Class-based construction of a verb lexicon. In Proceedings of the 17th National Conference on Artificial Intelligence (AAAI-2000) and Twelfth Conference on Innovative Applications of Artificial Intelligence, American Association for Artificial Intelligence (AAAI) Press. Texas, USA, pp. 691–696.Google Scholar
Kroch, A. S., and Joshi, A. K. 1985. The linguistic relevance of tree adjoining grammars. Technical Report MS-CIS-85-16. Department of Computer and Information Science, University of Pennsylvania.Google Scholar
Lee, L., 2002. Fast context-free grammar parsing requires fast boolean matrix multiplication. Journal of the ACM (JACM) 49 (1): 1–15.CrossRefGoogle Scholar
Ma, W.-Y., and McKeown, K., 2012. Detecting and correcting syntactic errors in machine translation using feature-based lexicalized tree adjoining grammars. International Journal of Computational Linguistics and Chinese Language Processing (IJCLCLP) 17 (4): 1–14.Google Scholar
Marcus, M. P., Santorini, B., and Marcinkiewicz, M. A. 1993. Building a arge annotated corpus of English: the penn treebank. Computational Linguistics - Special issue on using large corpora 19 (2): 313–330.Google Scholar
Park, J. 2006. Extraction of tree adjoining grammars from a treebank for Korean. In Proceedings of the 21st International Conference on computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop, ACL 2006. Association for Computational Linguistics. Sydney, Australia, pp. 73–78.Google Scholar
Pollard, C., and Sag, I. A. 1994. Head-Driven Phrase Structure Grammar, University of Chicago Press.Google Scholar
Ratnaparkhi, A., 1996. A maximum entropy model for Part-Of-Speech tagging. In Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP 1996, Association for Computational Linguistics. Philadelphia, USA. vol. 1, pp. 133–142.Google Scholar
Ryant, N., and Kipper, K., 2004. Assigning XTAG trees to VerbNet. In Proceedings of the 7th International Workshop on Tree Adjoining Grammar and Related Formalisms, TAG+ 7. Vancouver, BC, CA, pp. 194–198.Google Scholar
Sarkar, A. 2007. Combining Supertagging and Lexicalized Tree-Adjoining Grammar Parsing. Complexity of Lexical Descriptions and its Relevance to Natural Language Processing: A Supertagging Approach. MIT Press, Boston, MA, USA.Google Scholar
Satta, G., 1994. Tree-adjoining grammar parsing and boolean matrix multiplication. Computational Linguistics 20 (2): 173–191.Google Scholar
Schabes, Y., and Joshi, A. K., 1988. An Earley-type parsing algorithm for tree adjoining grammars. In Proceedings of the 26th Annual Meeting on Association for Computational Linguistics., ACL 1988. Association for Computational Linguistics. Buffalo, New York, USA, pp. 258–269.CrossRefGoogle Scholar
Schabes, Y., and Waters, R. C., 1995. Tree insertion grammar: a cubic-time, parsable formalism that lexicalizes context-free grammar without changing the trees produced. Computational Linguistics 21 (4): 479–513.Google Scholar
Shieber, S. M., and Schabes, Y., 1990. Synchronous tree-adjoining grammars. In Proceedings of the 13th Conference on Computational linguistics, COLING 1990. Association for Computational Linguistics. University of Helsinki, Finland. vol. 3, pp. 253–258.CrossRefGoogle Scholar
Steedman, M., 2000. The Syntactic Process. Cambridge, MA, USA: MIT Press.Google Scholar
Stone, M., and Doran, C., 1997. Sentence planning as description using tree adjoining grammar. In Proceedings of the 35th Annual Meeting of the Association for Computational Linguistics and 8th Conference of the European Chapter of the Association for Computational Linguistics, EACL 1998. Association for Computational Linguistics. Madrid, Spain, pp. 198–205.Google Scholar
Xia, F. 1999. Extracting tree adjoining grammars from bracketed corpora. In Proceedings of the 5th Natural Language Processing Pacific Rim Symposium. NLPRS 1999. Beijing, China, pp. 398–403.Google Scholar
Xia, F. 2001. Automatic grammar generation from two different perspectives, Ph.D. thesis, University of Pennsylvania.Google Scholar
Xia, F., and Palmer, M., 2000. Evaluating the Coverage of LTAGs on Annotated Corpora. In Proceedings of LREC satellite workshop Using Evaluation within HLT Programs: Results and Trends, Athens, Greece, pp. 1–6.Google Scholar
XTAG-Group. 2001. A Lexicalized Tree Adjoining Grammar for English. Technical report IRCS 01–03, Institute for Research in Cognitive Science, University of Pennsylvania.Google Scholar