ABSTRACT
Recent contributions to statistical language modeling for speech recognition have shown that probabilistically parsing a partial word sequence aids the prediction of the next word, leading to "structured" language models that have the potential to outperform n-grams. Existing approaches to structured language modeling construct nodes in the partial parse tree after all of the underlying words have been predicted. This paper presents a different approach, based on probabilistic left-corner grammar (PLCG) parsing, that extends a partial parse both from the bottom up and from the top down, leading to a more focused and more accurate, though somewhat less robust, search of the parse space. At the core of our new structured language model is a fast context-sensitive and lexicalized PLCG parsing algorithm that uses dynamic programming. Preliminary perplexity and word-accuracy results appear to be competitive with previous ones, while speed is increased.
- James K. Baker. 1979. Trainable grammars for speech recognition. In Jared J. Wolf and Dennis H. Klatt, editors, Speech Communication Papers for the 97th Meeting of the Acoustical Society of America, pages 547--550. The MIT Press, Cambridge, MA.Google Scholar
- Eugene Charniak. 2000. A maximum-entropy inspired parser. In Proc. of the NAACL, pages 132--139. Google ScholarDigital Library
- Ciprian Chelba. 2000. Exploiting Syntactic Structure for Natural Language Modeling. Ph.D. thesis, Johns Hopkins University. Google ScholarDigital Library
- Michael J. Collins. 1996. A new statistical parser based on bigram lexical dependencies. In Proc. of the 34th Annual Meeting of the ACL, pages 184--191. Google ScholarDigital Library
- Frederick Jelinek and Ciprian Chelba. 1999. Putting language into language modeling. In Proc. of Eurospeech '99, volume I, pages KN-1-6.Google Scholar
- Frederik Jelinek and John Lafferty. 1991. Computation of the probability of initial substring generation by stochastic context-free grammars. Computational Linguistics, 17(3):315--323. Google ScholarDigital Library
- Frederick Jelinek. 1997. Statistical Methods for Speech Recognition. The MIT Press, Cambridge, MA. Google ScholarDigital Library
- Slava M. Katz. 1987. Estimation of probabilities from sparse data for the language model component of a speech recognizer. IEEE Trans. on Acoustics, Speech and Signal Processing, 35:400--401.Google ScholarCross Ref
- David M. Magerman. 1994. Natural Language Parsing as Statistical Pattern Recognition. Ph.D. thesis, Stanford University. Google ScholarDigital Library
- Christopher D. Manning and Bob Carpenter. 1997. Probabilistic parsing using left corner language models. In Proc. of the Fifth International Workshop on Parsing Technologies, pages 147--158.Google Scholar
- Christopher D. Manning and Hinrich Schütze. 1999. Foundations of Statistical Natural Language Processing. The MIT Press, Cambridge, MA. Google ScholarDigital Library
- Mitchell P. Marcus, Beatrice Santorini, and Mary Ann Marcinkiewicz. 1995. Building a large annotated corpus of English: the Penn Tree-bank. Computational Linguistics, 19(2):313--330. Google ScholarDigital Library
- Brian Roark and Mark Johnson. 2000. Efficient probabilistic top-down and left-corner parsing. In Proc. of the 37th Annual Meeting of the ACL, pages 421--428. Google ScholarDigital Library
- Andreas Stolcke. 1995. An efficient probabilistic context-free parsing algorithm that computes prefix probabilities. Computational Linguistics, 21(2):165--201. Google ScholarDigital Library
- Filip Van Aelten and Marc Hogenhout. 2000. Inside-outside reestimation of Chelba-Jelinek models. Internal Report L&H--SR--00--027, Lernout & Hauspie, Wemmel, Belgium.Google Scholar
- Dong Hoon Van Uytsel. 2000. Earley-inspired parsing language model: Background and preliminaries. Internal Report PSI-SPCH-00-1, K.U.Leuven, ESAT, Heverlee, Belgium.Google Scholar
- A structured language model based on context-sensitive probabilistic left-corner parsing
Recommendations
A context-sensitive model for probabilistic LR parsing of spoken language with transformation-based postprocessing
COLING '00: Proceedings of the 18th conference on Computational linguistics - Volume 2This paper describes a hybrid approach to spontaneous speech parsing. The implemented parser uses an extended probabilistic LR parsing model with rich context and and its output is post-processed by a symbolic tree transformation routine that tries to ...
Left recursion in Parsing Expression Grammars
Parsing Expression Grammars (PEGs) are a formalism that can describe all deterministic context-free languages through a set of rules that specify a top-down parser for some language. PEGs are easy to use, and there are efficient implementations of PEG ...
Comments