Accurate semantic class classifier for coreference resolution
Published 1 January 2009Open access
Zhiheng Huang, Guangping Zeng, Weiqun Xu, Aslı Çelikyılmaz
Citations6
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
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.
Abstract
There have been considerable attempts to incorporate semantic knowledge into coreference resolution systems: different knowledge sources such as WordNet and Wikipedia have been used to boost the performance. In this paper, we propose new ways to extract WordNet feature. This feature, along with other features such as named entity feature, can be used to build an accurate semantic class (SC) classifier. In addition, we analyze the SC classification errors and propose to use relaxed SC agreement features. The proposed accurate SC classifier and the relaxation of SC agreement features on ACE2 coreference evaluation can boost our baseline system by 10.4% and 9.7% using MUC score and anaphor accuracy respectively.
Keywords
Computer Science
Computational LinguisticsA maximum entropy approach to natural language processing
3,120 Citations1996Adam Berger, Vincent J. Della Pietra +1 more
A maximum-likelihood approach for automatically constructing maximum entropy models is presented and how to implement this approach efficiently is described, using as examples several problems in natural language processing.
Incorporating non-local information into information extraction systems by Gibbs sampling
3,035 Citations2005Jenny Rose Finkel, Trond Grenager +1 more
By using simulated annealing in place of Viterbi decoding in sequence models such as HMMs, CMMs, and CRFs, it is possible to incorporate non-local structure while preserving tractable inference.
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.
Automatic retrieval and clustering of similar words
1,555 Citations1998Dekang Lin
A word similarity measure based on the distributional pattern of words allows the automatically constructed thesaurus to be significantly closer to WordNet than Roget Thesaurus is.
Computational LinguisticsA Machine Learning Approach to Coreference Resolution of Noun Phrases
998 Citations2001Wee Meng Soon, Hwee Tou Ng +1 more
The learning approach to coreference resolution of noun phrases in unrestricted text is presented, indicating that on the general noun phrase coreference task, the learning approach holds promise and achieves accuracy comparable to that of nonlearning approaches.
A model-theoretic coreference scoring scheme
682 Citations1995Marc Vilain, John D. Burger +3 more
This note describes a scoring scheme for the coreference task in MUC6 that improves on the original approach by grounding the scoring scheme in terms of a model; producing more intuitive recall and precision scores; and not requiring explicit computation of the transitive closure of coreference.
Proceedings of the 17th international conference on Computational linguistics -Automatic retrieval and clustering of similar words
550 Citations1998Dekang Lin
An intrinsic information content metric for semantic similarity in WordNet
526 Citations2004Nuno Seco, Tony Veale +1 more
A wholly intrinsic measure of Information Content that relies on hierarchical structure alone is presented, which is consequently easier to calculate, yet when used as the basis of a similarity mechanism it yields judgments that correlate more closely with human assessments than other, extrinsic measures of IC that additionally employ corpus analysis.
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.
Conditional Models of Identity Uncertainty with Application to Noun Coreference
233 Citations2004Andrew McCallum, Ben Wellner
Several discriminative, conditional-probability models for coreference analysis are introduced, all examples of undirected graphical models that can incorporate a great variety of features of the input without having to be concerned about their dependencies.
A mention-synchronous coreference resolution algorithm based on the Bell tree
220 Citations2004Xiaoqiang Luo, Abe Ittycheriah +3 more
A new approach for coreference resolution is proposed which uses the Bell tree to represent the search space and casts the coreference Resolution problem as finding the best path from the root of theBell tree to the leaf nodes.
Computational LinguisticsAn Empirically Based System for Processing Definite Descriptions
198 Citations2000Renata Vieira, Massimo Poesio
The annotated corpus was used to extensively evaluate the proposed techniques for matching definite descriptions with their antecedents, discourse segmentation, recognizing discourse-new descriptions, and suggesting anchors for bridging descriptions.
INRIA a CCSD electronic archive serverJoint Determination of Anaphoricity and Coreference Resolution using Integer Programming
154 Citations2007Pascal Denis, Jason Baldridge
This paper proposes an integer linear programming (ILP) formulation for coreference resolution which models anaphoricity and coreference as a joint task, such that each local model informs the other for the final assignments.
Optimization, maxent models, and conditional estimation without magic
150 Citations2003Christopher D. Manning, Dan Klein
This tutorial aims to cover the basic ideas and algorithms behind techniques such as maximum entropy modeling, conditional estimation of generative probabilistic models, and issues regarding the use of models more complex than simple Naive Bayes and Hidden Markov Models, using graphical illustrations rather than detailed derivations whenever possible.
BART: A modular toolkit for coreference resolution
137 Citations2008Yannick Versley, Simone Paolo Ponzetto +6 more
Learning to resolve bridging references
103 Citations2004Massimo Poesio, Rahul Mehta +2 more
This work uses machine learning techniques to find the best combination of local focus and lexical distance features for identifying the anchor of mereological bridging references using either Google or WordNet.
Text and knowledge mining for coreference resolution
89 Citations2001Sanda M. Harabagiu, Răzvan Bunescu +1 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.
BestCut
73 Citations2006Cristina Nicolae, Gabriel Nicolae
A coreference resolution method that employs a classification and a clusterization phase that is produced as a graph cutting algorithm, in which nodes of the graph correspond to the mentions of the text, whereas the edges of thegraph constitute the confidences derived from the coreference classification.
Computational LinguisticsComparing Knowledge Sources for Nominal Anaphora Resolution
64 Citations2005Katja Markert, Malvina Nissim
In studies, the Web-based method alleviated the lexical knowledge gap often encountered in anaphora resolution and handled examples with context-dependent relations between anaphor and antecedent.
PLoS ONEThe (Non)Utility of Predicate-Argument Frequencies for Pronoun Interpretation.
64 Citations2004Andrew Kehler, Douglas E. Appelt +2 more
The recombinant protein SviDyP could efficiently decolorize several triarylmethane dyes, anthraquinonic and azo dyes under neutral to alkaline conditions and showed broad pH adaptability and alkali-tolerance, making it a promising enzyme for use in the pulp and paper industries.
International Joint Conference on Artificial IntelligenceShallow semantics for coreference resolution
63 Citations2007Vincent Ng
Experiments on the ACE data sets indicate that the addition of these new semantic features to a coreference system employing a fairly standard feature set significantly improves its performance.
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.
Using Collocation Statistics in Information Extraction
45 Citations1998Dekang Lin
The main objective in participating MUC-7 is to investigate and experiment with the use of collocation statistics in information extraction, which refers to the frequency counts of the collocational relations extracted from a parsed corpus.
Factorizing complex models
43 Citations2006Radu Florian, Hongyan Jing +2 more
Three methods of assigning related tags in the mention detection and recognition project, with the goal of identifying named, nominal or pronominal references to real-world entities and labeling them with three types of information: entity type, entity subtype and mention type are investigated.