Intricacies of Collins' Parsing Model
Computational LinguisticsPublished 25 November 2004Open access
Daniel M. Bikel
Citations265
SJR quartileQ1
SJR score1.15
SNIP4.16
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
A large set of heretofore unpublished details Collins used in his parser are documents, such that, along with Collins' (1999) thesis, this article contains all information necessary to duplicate Collins' benchmark results.
Abstract
This article documents a large set of heretofore unpublished details Collins used in his parser, such that, along with Collins' (1999) thesis, this article contains all information necessary to duplicate Collins' benchmark results. Indeed, these as-yet-unpublished details account for an 11% relative increase in error from an implementation including all details to a clean-room implementation of Collins' model. We also show a cleaner and equally well-performing method for the handling of punctuation and conjunction and reveal certain other probabilistic oddities about Collins' parser. We not only analyze the effect of the unpublished details, but also reanalyze the effect of certain well-known details, revealing that bilexical dependencies are barely used by the model and that head choice is not nearly as important to overall parsing performance as once thought. Finally, we perform experiments that show that the true discriminative power of lexicalization appears to lie in the fact that unlexicalized syntactic structures are generated conditioning on the headword and its part of speech.
Keywords
Computer ScienceArts and Humanities
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
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.
Computational LinguisticsAutomatic Labeling of Semantic Roles
1,647 Citations2002Daniel Gildea, Daniel Jurafsky
Maximum Entropy Model for Part-Of-Speech Tagging
1,276 Citations1996Adwait Ratnaparkhi
A statistical model which trains from a corpus annotated with Part Of Speech tags and assigns them to previously unseen text with state of the art accuracy and discusses the corpus consistency problems discovered during the implementation of these features.
Three generative, lexicalised models for statistical parsing
749 Citations1997Michael Collins
A new statistical parsing model is proposed, which is a generative model of lexicalised context-free grammar and extended to include a probabilistic treatment of both subcategorisation and wh-movement.
IEEE Transactions on Information TheoryThe zero-frequency problem: estimating the probabilities of novel events in adaptive text compression
726 Citations1991Ian H. Witten, Tim Bell
The authors propose the application of a Poisson process model of novelty, which ability to predict novel tokens is evaluated, and it consistently outperforms existing methods and offers a small improvement in the coding efficiency of text compression over the best method previously known.
Computer Speech & LanguageApplications of stochastic context-free grammars using the Inside-Outside algorithm
666 Citations1991Kimia Bazargan Lari, S. Young
Two applications in speech recognition of the use of stochastic context-free grammars trained automatically via the Inside-Outside Algorithm, used to model VQ encoded speech for isolated word recognition and compared directly to HMMs used for the same task are described.
Choice Reviews OnlineEmpirical methods for artificial intelligence
637 Citations1996
Empirical research exploratory data analysis basic issues in experiment design hypothesis testing and estimation computer-intensive statistical methods performance assessment explaining performance - interactions and dependencies modelling tactics for generalization.
Three new probabilistic models for dependency parsing
630 Citations1996Jason Eisner
Preliminary empirical results from evaluating the three models' parsing performance on annotated Wall Street Journal training text (derived from the Penn Treebank) suggest the generative model performs significantly better than the others, and does about equally well at assigning part-of-speech tags.
A new statistical parser based on bigram lexical dependencies
619 Citations1996Michael Collins
A new statistical parser which is based on probabilities of dependencies between head-words in the parse tree, which trains on 40,000 sentences in under 15 minutes and can be improved to over 200 sentences a minute with negligible loss in accuracy.
The Journal of the Acoustical Society of AmericaTrainable grammars for speech recognition
538 Citations1979James K. Baker
This paper presents a generalization of these algorithms to certain denumerable‐state, hidden Markov processes that permits automatic training of the stochastic analog of an arbitrary context free grammar.
New ranking algorithms for parsing and tagging
505 Citations2001Michael Collins, Nigel Duffy
New learning algorithms for natural language processing based on the perceptron algorithm are introduced, showing how the algorithms can be efficiently applied to exponential sized representations of parse trees, such as the "all subtrees" (DOP) representation described by (Bod 1998).
Discriminative Reranking for Natural Language Parsing
443 Citations2000Michael J. Collins
Computer Speech & LanguageThe estimation of stochastic context-free grammars using the Inside-Outside algorithm
380 Citations1990Kimia Bazargan Lari, S. Young
A novel pre-training algorithm is described which can give significant computational savings and the need for controlling the way that non-terminals are allocated to hidden processes is discussed and a solution is presented in the form of a grammar minimization procedure.
ScholarlyCommons (University of Pennsylvania)Bracketing Guidelines For Treebank II Style Penn Treebank Project
310 Citations1995Ann Bies, Mark Ferguson +2 more
Corpus Variation and Parser Performance
273 Citations2001Daniel Gildea
This work examines how other types of text might affect parser performance, and how portable parsing models are across corpora by comparing results for the Brown and WSJ corpora, and considers which parts of the parser’s probability model are particularly tuned to the corpus on which it was trained.
IEEE Transactions on ComputersApplying Probability Measures to Abstract Languages
232 Citations1973Taylor L. Booth, Richard A. Thompson
The problem of assigning a probability to each word of a language is considered and two methods are discussed.
The necessity of parsing for predicate argument recognition
218 Citations2001Daniel Gildea, Martha Palmer
The effect of parser accuracy on these systems' performance is quantified, and the question of whether a flatter "chunked" representation of the input can be as effective for the purposes of semantic role identification is examined.
Towards history-based grammars
145 Citations1993Ezra Black, Fred Jelinek +4 more
HBG incorporates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way and significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error.
Design of a multi-lingual, parallel-processing statistical parsing engine
132 Citations2002Daniel M. Bikel
Ever since the widespread availability of the Penn Treebank, there have been numerous, statistical parsers developed for English, e.g. [8], but to varying degrees these parsers and others---while very successful at the tasks for which they were designed---had the following limitations.
arXiv (Cornell University)Exploiting Diversity in Natural Language Processing: Combining Parsers
106 Citations2000John C. Henderson, Eric Brill
Three state-of-the-art statistical parsers are combined to produce more accurate parses, as well as new bounds on achievable Treebank parsing accuracy, and both parametric and non-parametric models are explored.
Towards history-based grammars
91 Citations1992Ezra Black, Fred Jelinek +4 more
HBG incorporates lexical, syntactic, semantic, and structural information from the parse tree into the disambiguation process in a novel way, and significantly outperforms P-CFG, increasing the parsing accuracy rate from 60% to 75%, a 37% reduction in error.
Two statistical parsing models applied to the Chinese Treebank
86 Citations2000Daniel M. Bikel, David Chiang
The first-ever results of applying statistical parsing models to the newly-available Chinese Treebank are presented, with the former performing at 69% precision, 75% recall, and the latter at 77% precision and 78% recall.
Recovering latent information in treebanks
76 Citations2002David Chiang, Daniel M. Bikel
This paper provides machinery to reduce the amount of human effort needed to adapt existing models to new corpora, and proposes a flexible notation for specifying these rules that would allow them to be shared by different models.
arXiv (Cornell University)Global Thresholding and Multiple Pass Parsing
47 Citations1997Joshua Goodman
A variation on classic beam thresholding techniques that is up to an order of magnitude faster than the traditional method, at the same performance level, and uses a new search algorithm to simultaneously optimize the thresholding parameters of the various algorithms.
A statistical model for parsing and word-sense disambiguation
29 Citations2000Daniel M. Bikel
A first attempt at a statistical model for simultaneous syntactic parsing and generalized word-sense disambiguation is described, which achieves a recall of 84.0% and a precision of 67.3% on a new data set constructed for the task.
On minimizing training corpus for parser acquisition
26 Citations2001Rebecca Hwa
It is found that tree-entropy can significantly reduce the amount of training annotation for both a history-basedparser and an EM-based parser, suggesting that the technique is parser independent.
Breaking the Resource Bottleneck for Multilingual Parsing
24 Citations2005Rebecca Hwa, Philip Resnik +1 more
A large-scale experiment is presented showing that Chinese dependency trees can be induced by using an English parser, a word alignment package, and a large corpus of sentence-aligned bilingual text, and it is found that a parser trained in this manner out-performs some simple baselines inspite of the noise in the induced treebank.