Metaheuristic Approaches to Lexical Substitution and Simplification

Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 870–880, Valencia, Spain, April 3-7, 2017. c⃝2017 Association for Computational Linguistics Metaheuristic Approaches to Lexical Substitution and Simplification Sallam Abualhaija Institute of Computer Technology Hamburg University of Technology sallam.abualhaija@tu-harburg.de Tristan Miller and Judith Eckle-Kohler and Iryna Gurevych Ubiquitous Knowledge Processing Lab (UKP-TUDA/UKP-DIPF/AIPHES) Department of Computer Science Technische Universit¨at Darmstadt https://www.ukp.tu-darmstadt.de/ Karl-Heinz Zimmermann Institute of Computer Technology Hamburg University of Technology K.Zimmermann@tu-harburg.de Abstract In this paper, we propose using metaheuris- tics—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 per- form such an extrinsic evaluation of meta- heuristics, 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. More- over, the D-Bees–based lexical substitu- tion system outperforms state-of-the-art systems on several evaluation metrics. We also show that D-Bees achieves competi- tive performance in lexical simplification, a variant of lexical substitution. 1 Introduction Lexical substitution is a special case of automatic paraphrasing in which the goal is to provide contex- tually appropriate replacements for a given word, such that the overall meaning of the context is main- tained. The task has applications in question an- swering, text summarization, sentence compres- sion, information extraction, machine translation, and natural language generation (Androutsopou- los and Malakasiotis, 2010). It is also frequently employed as an in vivo evaluation of word sense disambiguation (WSD) systems (McCarthy and Navigli, 2009; Toral, 2009; Miller et al., 2015), because while lexical substitution requires words to be sense-disambiguated, it does not impose use of a predefined sense inventory. Past work in WSD, whether or not it forms part of a lexical substitution system, has employed a wide range of approaches (Agirre and Edmonds, 2007). Supervised methods usually achieve the best results, but at the tremendous cost of produc- ing manually annotated training data specific to the language and domain. Knowledge-based and unsupervised methods rely only on pre-existing resources such as machine-readable dictionaries and raw corpora. Though generally less accurate, they have the advantage of being more flexible and more adaptable to new languages and domains. For knowledge-based methods, this has been especially true since the advent of large, multilingual, collab- oratively constructed resources such as Wikipedia and Wiktionary (Zesch et al., 2008). In this paper, we present two novel approaches to lexical substitution which are knowledge-based, generally language-independent, and use a com- bination of traditional wordnets and Wiktionary. The first approach uses simulated annealing (Kirk- patrick et al., 1983), which was first proposed for use in WSD by Cowie et al. (1992) but has attracted relatively little attention since then. The second ap- proach uses D-Bees (Abualhaija and Zimmermann, 2016), a relatively new, biologically inspired dis- ambiguation algorithm that models swarm intelli- gence. Both algorithms are metaheuristic …

Content truncated to 500 words