Edit-Constrained Decoding for Sentence Simplification

Autor:	Zetsu, Tatsuya, Arase, Yuki, Kajiwara, Tomoyuki
Rok vydání:	2024
Předmět:	Computer Science - Computation and Language Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	We propose edit operation based lexically constrained decoding for sentence simplification. In sentence simplification, lexical paraphrasing is one of the primary procedures for rewriting complex sentences into simpler correspondences. While previous studies have confirmed the efficacy of lexically constrained decoding on this task, their constraints can be loose and may lead to sub-optimal generation. We address this problem by designing constraints that replicate the edit operations conducted in simplification and defining stricter satisfaction conditions. Our experiments indicate that the proposed method consistently outperforms the previous studies on three English simplification corpora commonly used in this task. Comment: Accepted by EMNLP2024-Findings
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2409.19247 Zobrazit plný text záznamu View this record from Arxiv