A Context-Driven Merge-Sort Model for Community-Oriented Lexical Simplification

Rongying Li, Wenxiu Xie, Jiayin Song, Leung Pun Wong, Fu Lee Wang, Tianyong Hao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Lexical simplification aims to convert complex words in a sentence into semantic equivalent but simple words. Most existing methods ignore sentence contextual information, which inevitably produces a large number of spurious substitute candidates. To that end, this paper proposes a new context-driven Merge-sort model which leverages contextual information in each step of lexical simplification, and a new merging method to combine ranking results produced by the proposed model. Based on standard datasets, our model outperforms a list of baselines including the state-of-the-art LSBert model, indicating its effectiveness in community-oriented lexical simplification.

Original languageEnglish
Title of host publicationISPCE-ASIA 2022 - IEEE International Symposium on Product Compliance Engineering - Asia 2022
ISBN (Electronic)9798350332483
DOIs
Publication statusPublished - 2022
Event2022 IEEE International Symposium on Product Compliance Engineering - Asia, ISPCE-ASIA 2022 - Guangzhou, China
Duration: 4 Nov 20226 Nov 2022

Publication series

NameISPCE-ASIA 2022 - IEEE International Symposium on Product Compliance Engineering - Asia 2022

Conference

Conference2022 IEEE International Symposium on Product Compliance Engineering - Asia, ISPCE-ASIA 2022
Country/TerritoryChina
CityGuangzhou
Period4/11/226/11/22

Keywords

  • Bert
  • Context2vec
  • Lexical simplification
  • Merge ranking

Fingerprint

Dive into the research topics of 'A Context-Driven Merge-Sort Model for Community-Oriented Lexical Simplification'. Together they form a unique fingerprint.

Cite this