TU Darmstadt / ULB / TUbiblio

Metaheuristic Approaches to Lexical Substitution and Simplification

Abualhaija, Sallam ; Miller, Tristan ; Eckle-Kohler, Judith ; Gurevych, Iryna ; Zimmermann, Karl-Heinz (2017)
Metaheuristic Approaches to Lexical Substitution and Simplification.
Valencia, Spain
Konferenzveröffentlichung, Bibliographie

Kurzbeschreibung (Abstract)

In this paper, we propose using metaheuristics---in particular, simulated annealing and the new D-Bees algorithm---to solve word sense disambiguation as an optimization problem within a knowledge-based lexical substitution system.  We are the first to perform such an extrinsic evaluation of metaheuristics, for which we use two standard lexical substitution datasets, one English and one German.  We find that D-Bees has robust performance for both languages, and performs better than simulated annealing, though both achieve good results.  Moreover, the D-Bees--based lexical substitution system outperforms state-of-the-art systems on several evaluation metrics.  We also show that D-Bees achieves competitive performance in lexical simplification, a variant of lexical substitution.

Typ des Eintrags: Konferenzveröffentlichung
Erschienen: 2017
Autor(en): Abualhaija, Sallam ; Miller, Tristan ; Eckle-Kohler, Judith ; Gurevych, Iryna ; Zimmermann, Karl-Heinz
Art des Eintrags: Bibliographie
Titel: Metaheuristic Approaches to Lexical Substitution and Simplification
Sprache: Englisch
Publikationsjahr: April 2017
Verlag: Association for Computational Linguistics
Buchtitel: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017)
Band einer Reihe: 1
Veranstaltungsort: Valencia, Spain
URL / URN: http://aclweb.org/anthology/E/E17/E17-1082.pdf
Kurzbeschreibung (Abstract):

In this paper, we propose using metaheuristics---in particular, simulated annealing and the new D-Bees algorithm---to solve word sense disambiguation as an optimization problem within a knowledge-based lexical substitution system.  We are the first to perform such an extrinsic evaluation of metaheuristics, for which we use two standard lexical substitution datasets, one English and one German.  We find that D-Bees has robust performance for both languages, and performs better than simulated annealing, though both achieve good results.  Moreover, the D-Bees--based lexical substitution system outperforms state-of-the-art systems on several evaluation metrics.  We also show that D-Bees achieves competitive performance in lexical simplification, a variant of lexical substitution.

Freie Schlagworte: UKP_reviewed;reviewed
ID-Nummer: TUD-CS-2017-0009
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Ubiquitäre Wissensverarbeitung
DFG-Graduiertenkollegs
DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen
Hinterlegungsdatum: 31 Dez 2016 14:29
Letzte Änderung: 24 Jan 2020 12:03
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen