Work

An incremental entity-mention model for coreference resolution with restrictive antecedent accessibility

Year: 2011

Type: conference-paper

Abstract: We introduce an incremental entity-mention model for coreference resolution. Our experiments show that it is superior to a non-incremental version in the same environment. The benefits of an incremental architecture are: a reduction of the number of candidate pairs, a means to overcome the problem of underspecified items in pairwise classification and the natural integration of global constraints such as transitivity. Additionally, we have defined a simple salience measure that - coupled with the incremental model - proved to establish a challenging baseline which seems to be on par with machine learning based systems of the 2010's SemEval shared task.

Source: Zurich Open Repository and Archive (University of Zurich)

DOI: 10.5167/uzh-49838

Authors: Klenner, M, Tuggener, D

Institution: University of Zurich

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W238727453

FWCI: 1.5

Cites: 21

Cited by: 17

Related to: 20