Linguistically motivated large-scale NLP with C&C and boxer
Published 1 January 2007Open access
James Curran, Stephen Clark, Johan Bos
Citations254
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
An NLP system which is based on syntactic and semantic formalisms from theoretical linguistics, and which is used to analyse the entire Gigaword corpus in less than 5 days using only 18 processors, represents a break-through in NLP technology.
Abstract
The statistical modelling of language, together with advances in wide-coverage grammar development, have led to high levels of robustness and efficiency in NLP systems and made linguistically motivated large-scale language processing a possibility (Matsuzaki et al., 2007; Kaplan et al., 2004). This paper describes an NLP system which is based on syntactic and semantic formalisms from theoretical linguistics, and which we have used to analyse the entire Gigaword corpus (1 billion words) in less than 5 days using only 18 processors. This combination of detail and speed of analysis represents a break-through in NLP technology.
Keywords
Computer Science
Computational LinguisticsHead-Driven Statistical Models for Natural Language Parsing
1,860 Citations2003Michael Collins
Three statistical models for natural language parsing are described, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree.
The MIT Press eBooksThe Syntactic Process
1,610 Citations2000Mark Steedman
The book covers topics in formal linguistics, intonational phonology, computational linguistics and experimental psycholinguistics, presenting them as an integrated theory of the language faculty in a form accessible to readers from any of those fields.
The second release of the RASP system
356 Citations2006Ted Briscoe, John M. Carroll +1 more
The new release of the RASP (robust accurate statistical parsing) system, designed for syntactic annotation of free text, is described, including a revised and more semantically-motivated output representation, an enhanced grammar and part-of-speech tagger lexicon, and a more flexible and semi-supervised training method for the structural parse ranking model.
Natural Language EngineeringApplied morphological processing of English
347 Citations2001Guido Minnen, John M. Carroll +1 more
Two newly developed computational tools for morphological processing are described: a program for analysis of English inflectional morphology, and a morphological generator, automatically derived from the analyser, which are fast, being based on finite-state techniques, and robust, in that they are able to deal effectively with unknown words.
Parsing the WSJ using CCG and log-linear models
279 Citations2004Stephen Clark, James Curran
A parallel implementation of the L-BFGS optimisation algorithm is described, which runs on a Beowulf cluster allowing the complete Penn Treebank to be used for estimation and a new efficient parsing algorithm for CCG which maximises expected recall of dependencies is developed.
Language independent NER using a maximum entropy tagger
249 Citations2003James Curran, Stephen Clark
This paper demonstrates that a maximum entropy tagger can effectively encode such information and identify named entities with very high accuracy.
Computational LinguisticsRepresentation and Inference for Natural Language: A First Course in Computational Semantics
219 Citations2006Francis Jeffry Pelletier
This book introduces fundamental techniques for computing semantic representations for fragments of natural language and performing inference with the result by using first-order logic and lambda calculus.
The importance of supertagging for wide-coverage CCG parsing
138 Citations2004Stephen Clark, James Curran
This paper describes the role of supertagging in a wide-coverage CCG parser which uses a log-linear model to select an analysis and shows that large increases in speed can be obtained by tightly integrating the supertagger with the CCG grammar and parser.
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)Speed and Accuracy in Shallow and Deep Stochastic Parsing
108 Citations2004Ronald M. Kaplan, Stefan Riezler +4 more
This paper reports some experiments that Compare the accuracy and performance of two stochastic parsing systems and found the deep-parsing system to be more accurate than the Collins parser with only a slight reduction in parsing speed.
Investigating GIS and smoothing for maximum entropy taggers
102 Citations2003James Curran, Stephen Clark
It is shown analytically and empirically that the correction feature, assumed to be required for the correctness of GIS, is unnecessary, and the use of a Gaussian prior and a simple cutoff for smoothing is explored.
Efficient HPSG parsing with supertagging and CFG-filtering
57 Citations2007Takuya Matsuzaki, Yusuke Miyao +1 more
An efficient parsing technique for HPSG is presented and it is shown that further speed-up is possible by eliminating non-parsable lexical entry sequences from the output of the supertagger.
Formalism-Independent Parser Evaluation with CCG and DepBank
55 Citations2007Stephen Clark, James Curran
This paper evaluates a CCG parser on DepBank, and demonstrates the difficulties in converting the parser output into DepBank grammatical relations, and presents a method for measuring the effectiveness of the conversion, which provides an upper bound on parsing accuracy.
Multi-tagging for lexicalized-grammar parsing
41 Citations2006James Curran, Stephen Clark +1 more
This work describes a multi-tagging approach which maintains a suitable level of lexical category ambiguity for accurate and efficient CCG parsing and extends this approach to the POS level to overcome errors introduced by automatically assigned POS tags.
Edinburgh Research Explorer (University of Edinburgh)Object-Extraction and Question-Parsing using CCG.
37 Citations2004Stephen Clark, Mark Steedman +1 more
A detailed evaluation of a CCG parser on object extraction dependencies found in WSJ text and a novel technique for porting the parser to a new domain, by creating new labelled data at the lexical category level only are proposed.
Text REtrieval ConferenceQuestion Answering with QED at TREC-2005
36 Citations2005Kisuh Ahn, Johan Bos +4 more
The backbone of the question-answering platform is QED, a linguistically-principled QA system, which performed significantly above the median accuracy score of all participating systems at TREC 2005 and experimented with external sources of knowledge to enhance the performance of QED.
Perceptron training for a wide-coverage lexicalized-grammar parser
13 Citations2007Stephen Clark, James Curran
This paper investigates perceptron training for a wide-coverage CCG parser and compares the perceptron with a log-linear model, and exploits the lexicalized nature of CCG by using a finite-state supertagger to do much of the parsing work, resulting in a highly efficient decoder.