Incorporating Contextual Cues in Trainable Models for Coreference Resolution
Published 1 January 2003
Ryu Iida, Kentaro Inui, Hiroya Takamura, Yūji Matsumoto
Citations66
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
We propose a method that incorporates various novel contextual cues into a machine learning for resolving coreference. Distinct characteristics of our model are (i) incorporating more linguistic features capturing contextual information that is more sophisticated than what is offered in Centering Theory, and (ii) a tournament model for selecting a referent. Our experiments show that this model significantly outperforms earlier machine learning approaches, such as Soon et al. (2001). 1
Keywords
Computer Science
TechnometricsStatistical Learning Theory
26,913 Citations1999Yuhai Wu, Vladimir Vapnik
Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
C4.5: Programs for Machine Learning
23,665 Citations1992J. R. Quinlan
A complete guide to the C4.5 system as implemented in C for the UNIX environment, which starts from simple core learning methods and shows how they can be elaborated and extended to deal with typical problems such as missing data and over hitting.
Cohesion in English
5,806 Citations2014Μ. Α. Κ. Halliday, Ruqaiya Hasan
Accurate methods for the statistics of surprise and coincidence
2,688 Citations1993Ted Dunning
Centering: A Framework for Modelling the Local Coherence of Discourse,
1,785 Citations1995Barbara J. Grosz, Aravind K. Joshi +1 more
Interactions between local coherence and choice of referring expressions are examined; it is argued that differences in coherence correspond in part to the inference demands made by different types of referring expressions, given a particular attentional state.
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.
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.
A Statistical Approach to Anaphora Resolution
221 Citations1998Niyu Ge, John Hale +1 more
An algorithm for identifying pronominal anaphora and two experiments based upon this algorithm are presented, which incorporate multiple anaphoras resolution factors into a statistical framework specifically the distance between the pronoun and the proposed antecedent, gender/number/animaticity of the proposal, governing head information and noun phrase repetition.
Evaluating automated and manual acquisition of anaphora resolution strategies
176 Citations1995Chinatsu Aone, Scott Bennett
This work uses Japanese newspaper articles tagged with discourse information as training examples for a machine learning algorithm which employs the C4.5 decision tree algorithm by Quinlan (Quinlan, 1993) to build an automatically trainable anaphora resolution system.
arXiv (Cornell University)Japanese Discourse and the Process of Centering
168 Citations1996Marilyn Walker, Sharon Cote +1 more
A property-sharing constraint in Centering
133 Citations1986Megumi Kameyama
A constraint is proposed in the Centering approach to pronoun resolution in discourse that requires that two pronominal expressions that retain the same Cb across adjacent utterances share a certain common grammatical property.
The influence of minimum edit distance on reference resolution
75 Citations2002Michael Strube, Stefan Rapp +1 more
A cheap, language and domain independent feature based on the minimum edit distance between strings yielded a significant improvement for data sets consisting of definite noun phrases and proper names, respectively.
Factors in anaphora resolution: they are not the only things that matter
58 Citations1997Ruslan Mitkov
The paper discusses the significance of factors in anaphora resolution and on the basis of a comparative study argues that what matters is not only a good set of reliable factors but also the strategy for their application.
Applying Co-Training to reference resolution
50 Citations2001Christoph Müller, Stefan Rapp +1 more
This paper is concerned with the question if Co-Training can significantly reduce the amount of manual labeling work and still produce a classifier with an acceptable performance.
Anaphora resolution of Japanese zero pronouns with deictic reference
47 Citations1996Hiromi Nakaiwa, Satoshi Shirai
According to a window test for 175 zero pronouns with deictic referent in a sentence set for the evaluation of Japanese-to-English machine translation systems, all of zero pronouns could be resolved consistently and correctly.
A probabilistic method for analyzing Japanese anaphora integrating zero pronoun detection and resolution
43 Citations2002Kazuhiro Seki, Atsushi Fujii +1 more
This paper proposes a method to analyze Japanese anaphora, in which zero pronouns are used to refer to preceding entities (antecedents) and integrates two probability parameters to perform zero pronoun detection and resolution in a single framework.
Zero pronoun resolution in Japanese discourse based on centering theory
42 Citations1996Manabu Okumura, Tamura Kouji
This paper presents a method to handle complex sentences with the centering theory and describes the framework that identifies the autecedents of zero pronouns in naturally occurring Japanese discourses and presents the evaluation of the framework with real discourses.
Cogniac: a discourse processing engine
28 Citations1995Frederick Breckenridge Baldwin, Aravind K. Joshi
I fortunately had the pleasure of several friends unrelated Penn who entertained me at key points, bolstered waining self-esteem, and just plain dragged me away from my dissertation.
Grammar for ellipsis resolution in Japanese
17 Citations2002Shigeko Nariyama
This paper elucidates the linguistic mechanisms for resolving ellipsis (zero anaphor) in Japanese sentences, which are structured in such a way to anchor the topic, which is predominantly the subject, and are cohesively sequenced with the topic as a pivot.
Feasibility study for ellipsis resolution in dialogues by machine-learning technique
11 Citations1998Yamamoto Kazuhide, Eiichiro Sumita
By investigating the decision tree, it is found that topic-dependent attributes are necessary to obtain high performance resolution, and that indispensable attributes vary according to the grammatical case.
Resolution of indirect anaphora in Japanese sentences using examples "X<i>no</i>Y (Y of X)"
11 Citations1999Masaki Murata, Hitoshi Isahara +1 more
A case frame dictionary for nouns that contains knowledge of the relationships between two nouns but no such dictionary presently exists is needed, and a way to construct a noun case frame Dictionary is proposed by using examples of "X no Y."