Detail publikace

BUT-TYPED: Using domain knowledge for computing typed similarity

OTRUSINA, L. SMRŽ, P.

Originální název

BUT-TYPED: Using domain knowledge for computing typed similarity

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

This paper deals with knowledge-based textprocessing which aims at an intuitive notionof textual similarity. Entities and relations relevantfor a particular domain are identified anddisambiguated by means of semi-supervisedmachine learning techniques and resulting annotationsare applied for computing typedsimilarityof individual texts.

Klíčová slova

entity extraction, semantic similarity

Autoři

OTRUSINA, L.; SMRŽ, P.

Rok RIV

2013

Vydáno

30. 6. 2013

Nakladatel

Association for Computational Linguistics

Místo

Atlanta

ISBN

978-1-937284-48-0

Kniha

Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity

Strany od

119

Strany do

123

Strany počet

5

BibTex

@inproceedings{BUT103581,
  author="Lubomír {Otrusina} and Pavel {Smrž}",
  title="BUT-TYPED: Using domain knowledge for computing typed similarity",
  booktitle="Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 1: Proceedings of the Main Conference and the Shared Task: Semantic Textual Similarity",
  year="2013",
  pages="119--123",
  publisher="Association for Computational Linguistics",
  address="Atlanta",
  isbn="978-1-937284-48-0"
}