An LLM-Enhanced Adversarial Editing System for Lexical Simplification

arXiv:2402.14704v1 Announce Type: new
Abstract: Lexical Simplification (LS) aims to simplify text at the lexical level. Existing methods rely heavily on annotated data, making it challenging to apply in low-resource scenarios. In this paper, we propose a novel LS method without parallel corpora. This method employs an Adversarial Editing System with guidance from a confusion loss and an invariance loss to predict lexical edits in the original sentences. Meanwhile, we introduce an innovative LLM-enhanced loss to enable the distillation of …

abstract adversarial annotated data apply arxiv cs.cl data editing guidance llm low making novel paper text type