Metaheuristic Approaches to Lexical Substitution and Simplification

Sallam Abualhaija, Tristan Miller, Judith Eckle-Kohler, Iryna Gurevych, Karl-Heinz Zimmermann


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.
Anthology ID:
E17-1082
Volume:
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers
Month:
April
Year:
2017
Address:
Valencia, Spain
Editors:
Mirella Lapata, Phil Blunsom, Alexander Koller
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
870–880
Language:
URL:
https://aclanthology.org/E17-1082
DOI:
Bibkey:
Cite (ACL):
Sallam Abualhaija, Tristan Miller, Judith Eckle-Kohler, Iryna Gurevych, and Karl-Heinz Zimmermann. 2017. Metaheuristic Approaches to Lexical Substitution and Simplification. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 870–880, Valencia, Spain. Association for Computational Linguistics.
Cite (Informal):
Metaheuristic Approaches to Lexical Substitution and Simplification (Abualhaija et al., EACL 2017)
Copy Citation:
PDF:
https://aclanthology.org/E17-1082.pdf