Bootstrapping statistical parsers from small datasets
Published 1 January 2003Open access
Mark Steedman, Miles Osborne, Anoop Sarkar, Stephen Clark, Rebecca Hwa, Julia Hockenmaier
Citations153
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
Experimental results show that unlabelled sentences can be used to improve the performance of statistical parsers and it is shown that boot-strapping continues to be useful, even though no manually produced parses from the target domain are used.
Abstract
We present a practical co-training method for bootstrapping statistical parsers using a small amount of manually parsed training material and a much larger pool of raw sentences. Experimental results show that unlabelled sentences can be used to improve the performance of statistical parsers. In addition, we consider the problem of boot-strapping parsers when the manually parsed training material is in a different domain to either the raw sentences or the testing material. We show that boot-strapping continues to be useful, even though no manually produced parses from the target domain are used.
Keywords
Computer Science
Building a Large Annotated Corpus of English: The Penn Treebank
7,528 Citations1993Mitchell P. Marcus
Combining labeled and unlabeled data with co-training
5,604 Citations1998Avrim Blum, Tom M. Mitchell
Unsupervised word sense disambiguation rivaling supervised methods
2,408 Citations1995David Yarowsky
An unsupervised learning algorithm for sense disambiguation that, when trained on unannotated English text, rivals the performance of supervised techniques that require time-consuming hand annotations.
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.
Analyzing the effectiveness and applicability of co-training
1,028 Citations2000Kamal Nigam, Rayid Ghani
It is demonstrated that when learning from labeled and unlabeled data, algorithms explicitly leveraging a natural independent split of the features outperform algorithms that do not and may out-perform algorithms not using a split.
Unsupervised Models for Named Entity Classification
817 Citations1999Michael Collins, Yoram Singer
It is shown that the use of unlabeled data can reduce the requirements for supervision to just 7 simple "seed" rules, gaining leverage from natural redundancy in the data.
Statistical parsing with a context-free grammar and word statistics
535 Citations1997Eugene Charniak
A parsing system based upon a language model for English that is, in turn, based upon assigning probabilities to possible parses for a sentence that outperforms previous schemes is described.
Enhancing Supervised Learning with Unlabeled Data
459 Citations2000Sally A. Goldman, Yan Zhou
A new semi-supervised learning method called co-learning that is designed to use unlabeled data to enhance standard supervised learning algorithms to leverage off the fact that they have different representations of the hypotheses and are likely to detect different patterns in labeled data.
Procedure for quantitatively comparing the syntactic coverage of English grammars
436 Citations1991Judith L. Klavans, Mark Liberman +12 more
The MIT Press eBooksPAC Generalization Bounds for Co-training
287 Citations2002Sanjoy Dasgupta, Michael L. Littman +1 more
A new PAC-style bound on generalization error is given which justifies both the use of confidences — partial rules and partial labeling of the unlabeled data — and theUse of an agreement-based objective function as suggested by Collins and Singer.
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.
Limitations of Co-Training for Natural Language Learning from Large Datasets
165 Citations2001David R. Pierce, Claire Cardie
This study examines the learning behavior of co-training on natural language processing tasks that typically require large numbers of training instances to achieve usable performance levels and proposes a moderately supervised variant of cotraining in which a human corrects the mistakes made during automatic labeling.
Bootstrapping
148 Citations2001Steven Abney
This chapter develops a new conception of the bootstrapping objection, according to which the problem with the idea that intentions provide reasons is that the problem with the idea that intentions provide reasons is that the authors find ourselves with a normative theory that issues incoherent advice.
Applying co-training methods to statistical parsing
144 Citations2001Anoop Sarkar
It is shown that training a statistical parser on the combined labeled and unlabeled data strongly out-performs training only on the labeled data.