Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task
Conference on Computational Natural Language LearningPublished 23 June 2011
Heeyoung Lee, Yves Peirsman, Anne Lynn S. Chang, Nathanael Chambers, Mihai Surdeanu, Dan Jurafsky
Citations347
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.
Abstract
This paper details the coreference resolution system submitted by Stanford at the CoNLL-2011 shared task. Our system is a collection of deterministic coreference resolution models that incorporate lexical, syntactic, semantic, and discourse information. All these models use global document-level information by sharing mention attributes, such as gender and number, across mentions in the same cluster. We participated in both the open and closed tracks and submitted results using both predicted and gold mentions. Our system was ranked first in both tracks, with a score of 57.8 in the closed track and 58.3 in the open track.
Keywords
Computer ScienceBiochemistry, Genetics and Molecular Biology
Improving machine learning approaches to coreference resolution
709 Citations2001Vincent Ng, Claire Cardie
A noun phrase coreference system that extends the work of Soon et al. (2001) and produces the best results to date on the M UC-6 and MUC-7 coreference resolution data sets --- F-measures of 70.4 and 63.4, respectively.
LinguaResolving pronoun references
615 Citations1978Jerry R. Hobbs
It is shown in a detailed treatment of several examples how semantic analysis locates the antecedents of most pronouns as a by-product in a comprehensive system for semantic analysis of English texts.
Overview of BioNLP'09 shared task on event extraction
598 Citations2009Jin-Dong Kim, Tomoko Ohta +3 more
The design and implementation of the BioNLP'09 Shared Task is presented, indicating that state-of-the-art performance is approaching a practically applicable level and revealing some remaining challenges.
A Multi-Pass Sieve for Coreference Resolution
326 Citations2010Karthik Raghunathan, Heeyoung Lee +5 more
This work proposes a simple coreference architecture based on a sieve that applies tiers of deterministic coreference models one at a time from highest to lowest precision, and outperforms many state-of-the-art supervised and unsupervised models on several standard corpora.
CoNLL-2011 Shared Task: Modeling Unrestricted Coreference in OntoNotes
273 Citations2011Sameer Pradhan, Lance Ramshaw +4 more
The CoNLL-2011 shared task involved predicting coreference using OntoNotes data, a new resource that provides multiple integrated annotation layers (parses, semantic roles, word senses, named entities and coreference) that could support joint models.
Understanding the value of features for coreference resolution
257 Citations2008Eric Bengtson, Dan Roth
This paper describes a rather simple pairwise classification model for coreference resolution, developed with a well-designed set of features and shows that this produces a state-of-the-art system that outperforms systems built with complex models.
Exploiting semantic role labeling, WordNet and Wikipedia for coreference resolution
256 Citations2006Simone Paolo Ponzetto, Michael Strube
An extension of a machine learning based coreference resolution system which uses features induced from different semantic knowledge sources, which represent knowledge mined from WordNet and Wikipedia, as well as information about semantic role labels is presented.
Language<b>Discourse structure and anaphora:</b> Written and conversational English. By Barbara Fox. Cambridge & New York: Cambridge University Press. 1993. Pp. v, 173.
211 Citations1995Jeanette Κ. Gundel
Coreference Resolution in a Modular, Entity-Centered Model
144 Citations2010Aria Haghighi, Dan Klein
This generative, model-based approach in which each of these factors is modularly encapsulated and learned in a primarily unsu-pervised manner is presented, resulting in the best results to date on the complete end-to-end coreference task.
CogNIAC
128 Citations1997Breck Baldwin
It is suggested that the system is resolving a sub-set of anaphors that do not require general world knowledge or sophisticated linguistic processing for successful resolution, and is very likely that they are largely domain independent and that they reflect processing strategies used by humans for general language comprehension.
International Conference on Semantic Computing (ICSC 2007)Elements of a National SemanticWeb Infrastructure--Case Study Finland on the Semantic Web
117 Citations2007Eero Hyvönen, Robin Lindroos +14 more
A large-scale exploration of effective global features for a joint entity detection and tracking model
83 Citations2005Hal Daumé, Daniel Marcu
A new joint EDT model is developed and the utility of many features are explored, demonstrating their effectiveness on this task.
Coreference Resolution Using Semantic Relatedness Information from Automatically Discovered Patterns
52 Citations2007Xiaofeng Yang, Jian Su
An approach that can automatically find the effective patterns for coreference resolution and explore how to automatically discover and evaluate patterns, and how to exploit the patterns to obtain the semantic relatedness information is proposed.
Semantic Class Induction and Coreference Resolution
52 Citations2007Vincent Ng
This paper examines whether a learningbased coreference resolver can be improved using semantic class knowledge that is automatically acquired from a version of the Penn Treebank in which the noun phrases are labeled with their semantic classes.
Pacific Asia Conference on Language, Information, and ComputationGender and Animacy Knowledge Discovery from Web-Scale N-Grams for Unsupervised Person Mention Detection
38 Citations2009Heng Ji, Dekang Lin
A simple approach to discover gender and animacy knowledge for person mention detection by learning noun-gender and noun-animacy pair counts from web-scale n-grams using specific lexical patterns and applying confidence estimation metrics to filter noise.
Munich Personal RePEc Archive (Ludwig Maximilian University of Munich)Dialogue Structure and Pronoun Resolution
11 Citations2006Joel Tetreault, James F. Allen
The results show that incorporating this shallow segmentation at best marginally improves pronoun resolution performance in a task-oriented corpus of dialogues.
An Empirical Evaluation of Pronoun Resolution and Clausal Structure
7 Citations2003Joel Tetreault, James F. Allen
An automated empirical evaluation of the relationship between clausal structure and pronominal reference and develops and evaluates two pronoun resolution algorithms that incorporate clausal and discourse structure.
Accurate semantic class classifier for coreference resolution
6 Citations2009Zhiheng Huang, Guangping Zeng +2 more
New ways to extract WordNet feature, along with other features such as named entity feature, can be used to build an accurate semantic class (SC) classifier and the relaxation of SC agreement features on ACE2 coreference evaluation are proposed.