Event-based textual document retrieval by using semantic role labeling and coreference resolution - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2007

Event-based textual document retrieval by using semantic role labeling and coreference resolution

Abstract

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”, such as “Einstein discovered relativity”. This paper proposes a framework to resolve such a problem. In our proposal, we apply semantic role labeling and coreference techniques in order to parse each sentence within textual documents into three elements: subject, object and predicates. These elements can subsequently be used for indexing and retrieval. Our primitive evaluation experiments have shown that this promising methodology raises the retrieval precision if we compared it to conventional literal termmatching techniques.
Fichier principal
Vignette du fichier
IADIS-event-search-final.pdf (194.35 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

inria-00192465 , version 1 (28-11-2007)

Identifiers

  • HAL Id : inria-00192465 , version 1

Cite

Chia-Hung Lin, Chia-Wei Yen, Jen-Shin Hong, Samuel Cruz-Lara. Event-based textual document retrieval by using semantic role labeling and coreference resolution. IADIS International Conference WWW/Internet 2007, Oct 2007, Vila Real, Portugal. ⟨inria-00192465⟩
120 View
189 Download

Share

Gmail Facebook Twitter LinkedIn More