Options
Metaheuristic approaches to lexical substitution and simplification
Citation Link: https://doi.org/10.15480/882.2432
Publikationstyp
Conference Paper
Date Issued
2017
Sprache
English
Institut
TORE-DOI
TORE-URI
Volume
1
Start Page
870
End Page
880
Citation
15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017 - Proceedings of Conference (1): 870-880 (2017)
Contribution to Conference
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.
DDC Class
600: Technik
More Funding Information
This work was supported in part by the research training group Adaptive Preparation of Information from Heterogeneous Sources (AIPHES,
GRK1994/1) and by the German Institute for Educational Research (DIPF).
GRK1994/1) and by the German Institute for Educational Research (DIPF).
Loading...
Name
E17-1082.pdf
Size
281.9 KB
Format
Adobe PDF