DMCA
Using background knowledge to support coreference resolution (2010)
| Venue: | In Proceedings of ECAI |
| Citations: | 10 - 1 self |
BibTeX
@INPROCEEDINGS{Bryl10usingbackground,
author = {Volha Bryl and Claudio Giuliano and Luciano Serafini and Kateryna Tymoshenko},
title = {Using background knowledge to support coreference resolution},
booktitle = {In Proceedings of ECAI},
year = {2010}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Abstract. Systems based on statistical and machine learning meth-ods have been shown to be extremely effective and scalable for the analysis of large amount of textual data. However, in the recent years, it becomes evident that one of the most important direction of improvement in natural language processing (NLP) tasks, like word sense disambiguation, coreference resolution, relation extrac-tion, and other tasks related to knowledge extraction, is by exploit-ing semantics. While in the past, the unavailability of rich and com-plete semantic descriptions constituted a serious limitation of their applicability, nowadays, the Semantic Web made available a large amount of logically encoded information (e.g. ontologies, RDF(S)-data, linked data, etc.), which constitute a valuable source of seman-tics. However, web semantics cannot be easily plugged into machine learning systems. Therefore the objective of this paper is to define a reference methodology for combining semantics information avail-able in the web under the form of logical theories, with statistical methods for NLP. The major problems that we have to solve to im-plement our methodology concern (i) the selection of the correct and minimal knowledge among the large amount available in the web, (ii) the representation of uncertain knowledge, and (iii) the resolu-tion and the encoding of the rules that combine knowledge retrieved from Semantic Web sources with semantics in the text. In order to evaluate the appropriateness of our approach, we present an applica-tion of the methodology to the problem of intra-document corefer-ence resolution, and we show by means of some experiments on the ACE 2005 dataset, how the injection of knowledge is correlated to the improvement of the performance of our approach on this tasks. 1
Keyphrases
coreference resolution background knowledge large amount serious limitation semantic web important direction exploit-ing semantics methodology concern major problem natural language processing uncertain knowledge valuable source textual data statistical method semantics information logical theory recent year semantic web source reference methodology com-plete semantic description word sense disambiguation relation extrac-tion minimal knowledge intra-document corefer-ence resolution
