Unsupervised Relation Extraction in Specialized Corpora Using Sequence Mining - Archive ouverte HAL Access content directly
Conference Papers Year : 2016

Unsupervised Relation Extraction in Specialized Corpora Using Sequence Mining

(1) , (1) , (2) , (1) , (1)
1
2

Abstract

This paper deals with the extraction of semantic relations from scientific texts. Pattern-based representations are compared to word embeddings in unsupervised clustering experiments, according to their potential to discover new types of semantic relations and recognize their instances. The results indicate that sequential pattern mining can significantly improve pattern-based representations, even in a completely unsupervised setting.
Fichier principal
Vignette du fichier
unsupervised-relation-extraction (2).pdf (334.81 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01405041 , version 1 (29-11-2016)

Identifiers

Cite

Kata Gábor, Haïfa Zargayouna, Isabelle Tellier, Davide Buscaldi, Thierry Charnois. Unsupervised Relation Extraction in Specialized Corpora Using Sequence Mining. XVIth Symposium on Intelligent Data Analysis, Oct 2016, Stockholm, Sweden. pp.237 - 248, ⟨10.1007/978-3-319-46349-0_21⟩. ⟨hal-01405041⟩
149 View
1052 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More