A Light-weight Approach to Coreference Resolution for Named Entities in Text

@inproceedings{Dimitrov2002ALA,
  title={A Light-weight Approach to Coreference Resolution for Named Entities in Text},
  author={M. Dimitrov and Kalina Bontcheva and H. Cunningham and D. Maynard},
  year={2002}
}
This paper presents a lightweight approach to pronoun resolution in the case when the antecedent is named entity. It falls under the category of the so-called "knowledge poor" approaches that do not rely extensively on linguistic and domain knowledge. We provide a practical implementation of this approach as a component of the General Architecture for Text Engineering (GATE). The results of the evaluation show that even such shallow and inexpensive approaches provide acceptable performance for… Expand

Tables and Topics from this paper

Coreference Resolution of Named Entities and Noun Phrases in Web Pages
An approach for intra-document coreference resolution of named entities and noun phrases is proposed. This approach is a knowledgepoor, integrated approach to coreference resolution which relies onExpand
Automatic identification of non-anaphoric anaphora in spoken dialog
TLDR
An automatic identification approach for non-anaphoric anaphora is presented, which is simpler and achieves a higher accuracy than the approaches used in the previous work. Expand
EVENT-BASED TEXTUAL DOCUMENT RETRIEVAL BY USING SEMANTIC ROLE LABELING AND COREFERENCE RESOLUTION
Conventional keyword-based indexing and retrieval techniques for textual documents lack of precision when a long query string is employed in order to discover documents containing a specific “event”,Expand
Logical-Ontological Approach to Coreference Resolution
We suggest a logical-ontological approach to the coreference resolution in the process of text analysis and information extraction. Our approach solves the problem of comparing objects found in theExpand
A Novel Text - Mining System for Generating Abstract from Extracted Summaries Using Anaphora Resolution
TLDR
A novel Abstract Generation System (AGS) to generate an abstract from the extracted summary of an English language text document and the results are compared with the model summary written by human beings. Expand
Automatic Detection of Nonreferential It in Spoken Multi-Party Dialog Christoph M üller EML Research gGmbH
We present an implemented machine learning system for the automatic detection of nonreferential it in spoken dialog. The system builds on shallow features extracted from dialog transcripts. OurExpand
An Extensive Evaluation of Anaphora Resolution Based Abstract Generation System
TLDR
An extensive evaluation of anaphora resolution (AR) algorithm proposed for Abstract Generation System (AGS) and the metrics used to measure its performance are discussed and its performances are studied with standard metrics of Information Extraction (IE) systems. Expand
MUSE: a MUlti-Source Entity recognition system
TLDR
The MUSE system incorporates a modular set of resources from which different subsets can be mixed and matched as required, and the process of selecting the correct resources depending on the text type is fully automatic. Expand
Towards large-scale, open-domain and ontology-based named entity classification
TLDR
The main contribution of the paper is a systematic analysis of the impact of varying certain parameters on such a context-based approach exploiting similarities in vector space for the disambiguation of named entities. Expand
An Algorithm for Anaphora Resolution in Aviation Safety Reports
TLDR
This paper constrain the domain of discourse by considering only aviation safety reports, and considers the task of pronominal resolution in the context of entity extraction in these aviation texts to provide an algorithm that is better suited to the task than general purpose anaphora resolution algorithms, and which should be applicable to other domains by incorporating similar constraints. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 49 REFERENCES
Robust Pronoun Resolution with Limited Knowledge
TLDR
This paper presents a robust, knowledge-poor approach to resolving pronouns in technical manuals, which operates on texts pre-processed by a part-of-speech tagger, and can be successfully adapted for other languages with minimum modifications. Expand
Overview of MUC-7
The task of Coreference (CO) had its origins in Semeval, an attempt after MUC-5 to define semantic research tasks that needed to be solved to be successful at generating scenario templates. In theExpand
Anaphora for Everyone: Pronominal Anaphora Resolution without a Parser
TLDR
Evaluation of the results of the implementation demonstrates that accurate anaphora resolution can be realized within natural language processing frameworks which do not---or cannot--- employ robust and reliable parsing components. Expand
Recognizing Referential Links: An Information Extraction Perspective
We present an efficient and robust reference resolution algorithm in an end-to-end state-of-the-art information extraction system, which must work with a considerably impoverished syntactic analysisExpand
Quantitative evaluation of coreference algorithms in an information extraction system
TLDR
The MUC-6 coreference task and the approach taken by the Large Scale Information Extraction (LaSIE) system developed at the University of Sheeeld are described, demonstrating both the utility of quantative analysis for assessing coreference algorithms and the exibility of the approach to coreference which provides a framework that facilitates experimentation with alternative techniques. Expand
CogNIAC: high precision coreference with limited knowledge and linguistic resources
TLDR
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. Expand
Evaluation Tool for Rule-based Anaphora Resolution Methods
TLDR
An evaluation environment for comparing anaphora resolution algorithms is proposed which is illustrated by presenting the results of the comparative evaluation of three methods on the basis of several evaluation measures. Expand
Using a semantic network for information extraction
TLDR
The LaSIE Information Extraction system's knowledge representation formalisms are described, their use in the IE task, and how the knowledge represented in them is acquired, including experiments to extend the system's coverage using the WordNet general purpose semantic network. Expand
Pronoun Resolution of "They" and "Them"
TLDR
This paper addresses the resolution of two pronouns, "they" and "them", and looks at simplistic rules to improve the process of determining the referent, beyond simply deciding the basis of most recent plural noun. Expand
A utomatic Resolution of Anaphora in English
TLDR
An algorithm is described for the automatic resolution of inter-sentential anaphoric references in English sentences that make use of both syntactic and morphological information about the sentence structure and real-world knowledge about the semantics of the sentence elements gained from several different sources to generate features for use in matching. Expand
...
1
2
3
4
5
...