Using Web-scale N-grams to Improve Base NP Parsing Performance

Using Web-scale N-grams to Improve Base NP Parsing Performance

Cached

Download Links

by Emily Pitler , Shane Bergsma , Dekang Lin , Kenneth Church

Citations:

BibTeX

@MISC{Pitler_usingweb-scale,
    author = {Emily Pitler and Shane Bergsma and Dekang Lin and Kenneth Church},
    title = {Using Web-scale N-grams to Improve Base NP Parsing Performance},
    year = {}
}

Bookmark

OpenURL

Abstract

We use web-scale N-grams in a base NP parser that correctly analyzes 95.4 % of the base NPs in natural text. Web-scale data improves performance. That is, there is no data like more data. Performance scales log-linearly with the number of parameters in the model (the number of unique N-grams). The web-scale N-grams are particularly helpful in harder cases, such as NPs that contain conjunctions. 1

Citations

1654	B.: Building a large annotated corpus of english: The Penn treebank - Marcus, Marcinkiewicz, et al. - 1993
627	Word association norms, mutual information, and lexicography - Church, Hanks - 1990
337	Text chunking using transformation-based learning - Ramshaw, Marcus - 1995
272	A Theory of Syntactic Recognition for Natural Language - Marcus - 1980
261	Coarse-to-Fine n-Best Parsing and MaxEnt Discriminative Reranking - Charniak, Johnson - 2005
220	Discriminative Reranking for Natural Language Parsing - Collins - 2000
209	Selection and Information: A ClassBased Approach to Lexical Relationships - Resnik - 1993
151	Y: Chunking with Support Vector Machines - Kudo, Matsumoto
124	Generating query substitutions - Jones, Rey, et al. - 2006
114	Max-margin parsing - Taskar, Klein, et al. - 2004
82	Scaling to very very large corpora for natural language disambiguation - Banko, Brill - 2001
78	Large language models in machine translation - Brants, Popat, et al. - 2007
58	Lexical semantic techniques for corpus analysis - Pustejovsky, Bergler, et al. - 1992
48	Web-based models for natural language processing - Lapata, Keller - 2005
36	Corpus Statistics Meet The Noun Compound: Some Empirical Results - Lauer - 1995
30	Efficient, Feature-based, Conditional Random Field Parsing - Finkel, Kleeman, et al. - 2008
29	The Stress and Structure of Modified Noun Phrases in English - Liberman, Sproat - 1992
24	Web 1T 5-gram corpus version 1.1 - Brants, Franz - 2006
24	Unsupervised query segmentation using generative language models and wikipedia - Tan, Peng
22	Search engine statistics beyond the n-gram: application to noun compound bracketing - Nakov, Hearst - 2003
22	A maximum entropy model for parsing - Ratnaparkhi, Roukos, et al. - 1994
18	New tools for web-scale n-grams - Lin, Church, et al. - 2010
15	The linguistic structure of English web-search queries - Barr, Jones, et al. - 2008
15	A unified and discriminative model for query refinement - Guo, Xu, et al. - 2008
14	Learning noun phrase query segmentation - Bergsma, Wang - 2007
14	Coping with syntactic ambiguity or how to put the block - Church, Patil - 1982
13	Semi-supervised sequential labeling and segmentation using giga-word scale unlabeled data - Suzuki, Isozaki - 2008
9	A trainable bracketer for noun modifiers - Barker - 1998
9	2007b. Large-scale supervised models for noun phrase bracketing - Vadas, Curran
7	Prepositional phrase attachment without oracles - Atterer, Schütze - 2007
2	A stochastic parts program and noun phrase parser for unrestricted text - W - 1988
2	Adding noun phrase structure to the penn treebank - 2007a