The Same-Head Heuristic for Coreference
Published 11 July 2010
Micha Elsner, Eugene Charniak
Citations8
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 unsupervised generative model is presented which learns not to link some same-head NPs using syntactic features, improving precision and investigating coreference relationships between NPs with the same head noun.
Abstract
We investigate coreference relationships between NPs with the same head noun. It is relatively common in unsupervised work to assume that such pairs are coreferent { but this is not always true, especially if realistic mention detection is used. We describe the distribution of non-coreferent same-head pairs in news and conversational discourse. We present an unsupervised generative model which learns not to link some same-head NPs using syntactic features. Our model improves precision on both news and conversation. 1.
Keywords
Computer Science
Effective self-training for parsing
619 Citations2006David McClosky, Eugene Charniak +1 more
This work presents a simple, but surprisingly effective, method of self-training a two-phase parser-reranker system using readily available unlabeled data and shows that this type of bootstrapping is possible for parsing when the bootstrapped parses are processed by a discriminative reranker.
On coreference resolution performance metrics
535 Citations2005Xiaoqiang Luo
The paper proposes a Constrained Entity-Alignment F-Measure (CEAF) for evaluating coreference resolution and shows that the best alignment is a maximum bipartite matching problem which can be solved by the Kuhn-Munkres algorithm.
Joint unsupervised coreference resolution with Markov logic
211 Citations2008Hoifung Poon, Pedro Domingos
This paper presents the first unsupervised approach that is competitive with supervised ones, made possible by performing joint inference across mentions, in contrast to the pairwise classification typically used in supervised methods, and by using Markov logic as a representation language.
Online EM for unsupervised models
210 Citations2009Percy Liang, Dan Klein
It is shown that online variants provide significant speedups and can even find better solutions than those found by batch EM on four unsupervised tasks: part-of-speech tagging, document classification, word segmentation, and word alignment.
Unsupervised models for coreference resolution
200 Citations2008Vincent Ng
A cluster-ranking approach to coreference resolution that combines the strengths of mention rankers and entity-mention models is proposed and Experimental results on the ACE data sets demonstrate its superior performance to competing approaches.
Simple coreference resolution with rich syntactic and semantic features
197 Citations2009Aria Haghighi, Dan Klein
This work presents a simple approach which completely modularizes these three aspects of coreference, which is deterministic and is driven entirely by syntactic and semantic compatibility as learned from a large, unlabeled corpus.
Language Resources and EvaluationThe NXT-format Switchboard Corpus: a rich resource for investigating the syntax, semantics, pragmatics and prosody of dialogue
174 Citations2010Sasha Calhoun, Jean Carletta +5 more
The approach to overcoming issues involved in such a data integration project is discussed, relevant to both users of the corpus and others in the language resource community undertaking similar projects.
Empirical estimates of adaptation
154 Citations2000Kenneth Church
Adaptation depends more on lexical content than frequency; there is more adaptation for content words, and less adaptation for function words, cliches and ordinary first names.
Meeting of the Association for Computational LinguisticsUnsupervised Coreference Resolution in a Nonparametric Bayesian Model
135 Citations2007Aria Haghighi, Dan Klein
An unsupervised, nonparametric Bayesian approach to coreference resolution which models both global entity identity across a corpus as well as the sequential anaphoric structure within each document is presented.
Conundrums in noun phrase coreference resolution
128 Citations2009Veselin Stoyanov, Nathan Gilbert +2 more
This work examines three subproblems that play a role in coreference resolution: named entity recognition, anaphoricity determination, and coreference element detection, and measures the performance of a state-of-the-art coreference resolver on several classes of anaphora.
Meeting of the Association for Computational LinguisticsAdding Noun Phrase Structure to the Penn Treebank
95 Citations2007David Vadas, James Curran
This paper details the process of adding gold-standard bracketing within each noun phrase in the Penn Treebank, and uses this resource to determine NP structure using several statistical approaches, thus demonstrating the utility of the corpus.
EM works for pronoun anaphora resolution
86 Citations2009Eugene Charniak, Micha Elsner
An algorithm for pronoun-anaphora (in English) that uses Expectation Maximization (EM) to learn virtually all of its parameters in an unsupervised fashion and significantly outperforms several systems available on the web.
An Annotation Scheme for Information Status in Dialogue
73 Citations2004Malvina Nissim, Shipra Dingare +2 more
An annotation scheme for information status (IS) in dialogue is presented, and validated on three Switchboard dialogues, to produce a corpus that contains nearly 70,000 NPs annotated for IS and over 15,000 coreference links.
Learning information status of discourse entities
64 Citations2006Malvina Nissim
This paper trains a decision tree to classify entities introduced by noun phrases as old, mediated, or new and compares its performance with hand-crafted rules that are mainly based on morpho-syntactic features and closely relate to the guidelines that had been used for the manual annotation.
An expectation maximization approach to pronoun resolution
33 Citations2005Colin Cherry, Shane Bergsma
The results indicate that a probabilistic gender/number model, determined automatically from unlabeled text, is a powerful feature for this task.
Neural Information Processing SystemsA Probabilistic Approach to Language Change
25 Citations2007Alexandre Bouchard‐Côté, Percy Liang +2 more
A probabilistic approach to language change in which word forms are represented by phoneme sequences that undergo stochastic edits along the branches of a phylogenetic tree is presented, which can be generalized to support inferences about linguistic phylogenies.
Competitive self-trained pronoun interpretation
15 Citations2004Andrew Kehler, Douglas E. Appelt +2 more
A system for pronoun interpretation that is self-trained from raw data, that is, using no annotated training data, which outperforms a Hobbsian baseline algorithm and is only marginally inferior to an essentially identical, state-of-the-art supervised model trained from a substantial manually-annotated coreference corpus.