Cited By
View all- Chen KTseng CTai C(2006)Predicting prosody from textProceedings of the 5th international conference on Chinese Spoken Language Processing10.1007/11939993_22(179-188)Online publication date: 13-Dec-2006
Linguistically-motivated grammar extraction, generalization and adaptation
Pages 177 - 187
Abstract
In order to obtain a high precision and high coverage grammar, we proposed a model to measure grammar coverage and designed a PCFG parser to measure efficiency of the grammar. To generalize grammars, a grammar binarization method was proposed to increase the coverage of a probabilistic context-free grammar. In the mean time linguistically-motivated feature constraints were added into grammar rules to maintain precision of the grammar. The generalized grammar increases grammar coverage from 93% to 99% and bracketing F-score from 87% to 91% in parsing Chinese sentences. To cope with error propagations due to word segmentation and part-of-speech tagging errors, we also proposed a grammar blending method to adapt to such errors. The blended grammar can reduce about 20~30% of parsing errors due to error assignment of pos made by a word segmentation system.
References
[1]
E. Charniak, and G. Carroll, "Context-sensitive statistics for improved grammatical language models." In Proceedings of the 12th National Conference on Artificial Intelligence, AAAI Press, pp. 742-747, Seattle, WA, 1994.
[2]
E. Charniak, "Treebank grammars." In Proceedings of the Thirteenth National Conference on Artificial Intelligence, pp. 1031-1036. AAAI Press/MIT Press, 1996.
[3]
E. Charniak, and G. Carroll, J. Adcock, A. Cassanda, Y. Gotoh, J. Katz, M. Littman, J. Mccann, "Taggers for Parsers", Artificial Intelligence, vol. 85, num. 1-2, 1996.
[4]
Feng-Yi Chen, Pi-Fang Tsai, Keh-Jiann Chen, and Huang, Chu-Ren, "Sinica Treebank." Computational Linguistics and Chinese Language Processing, 4(2):87-103, 2000.
[5]
Keh-Jiann Chen and, Yu-Ming Hsieh, "Chinese Treebanks and Grammar Extraction." the First International Joint Conference on Natural Language Processing (IJCNLP-04), March 2004.
[6]
Michael Collins, "Head-Driven Statistical Models for Natural Language parsing." Ph.D. thesis, Univ. of Pennsylvania, 1999.
[7]
Yu-Ming Hsieh, Duen-Chi Yang and Keh-Jiann Chen, "Grammar extraction, generalization and specialization. (in Chinese)" Proceedings of ROCLING 2004.
[8]
Christopher D. Manning and Hinrich Schutze, "Foundations of Statistical Natural Language Processing." the MIT Press, Cambridge, Massachusetts, 1999.
[9]
Mark Johnson, "PCFG models of linguistic tree representations." Computational Linguistics, Vol.24, pp.613-632, 1998.
[10]
Dan Klein and Christopher D. Manning, "Accurate Unlexicalized Parsing." Proceeding of the 4lst Annual Meeting of the Association for Computational Linguistics, pp. 423-430, July 2003.
[11]
Honglin Sun and Daniel Jurafsky, "Shallow Semantic Parsing of Chinese." Proceedings of NAACL 2004.
[12]
Hao Zhang, Qun Liu, Kevin Zhang, Gang Zou and Shuo Bai, "Statistical Chinese Parser ICTPROP." Technology Report, Institute of Computing Technology, 2003.
- Linguistically-motivated grammar extraction, generalization and adaptation
Recommendations
Chinese treebanks and grammar extraction
IJCNLP'04: Proceedings of the First international joint conference on Natural Language ProcessingPreparation of knowledge bank is a very difficult task. In this paper, we discuss the knowledge extraction from the manually examined Sinica Treebank. Categorical information, word-to-word relation, word collocations, new syntactic patterns and sentence ...
Towards a linguistically motivated computational grammar for Hebrew
Semitic '98: Proceedings of the Workshop on Computational Approaches to Semitic LanguagesWhile the morphology of Modern Hebrew is well accounted for computationally, there are few computational grammars describing the syntax of the language. Existing grammars are scarcely based on solid linguistic grounds: they do not conform to any ...
The Cognitive Interactionist Approach of Sentence Parsing with Simple Recurrent Networks
IITA '08: Proceedings of the 2008 Second International Symposium on Intelligent Information Technology Application - Volume 01Sentence parsing has a long research history in the fields of machine learning and natural language processing. The state-of-the-art techniques for tackling this task are mostly based on statistical language learning. How human parsing sentences is also ...
Comments
Information & Contributors
Information
Published In
Sponsors
- KAIST: Korea Advanced Institute of Science and Technology
- ETRI: Electronics and Telecommunications Research Institute
- Jeju Province Local Government: Jeju Province Local Government
- Microsoft Korea: Microsoft Korea
- KISTI
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 11 October 2005
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- View Citations1Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Nov 2024
Other Metrics
Citations
Cited By
View all- Chen KTseng CTai C(2006)Predicting prosody from textProceedings of the 5th international conference on Chinese Spoken Language Processing10.1007/11939993_22(179-188)Online publication date: 13-Dec-2006