用编辑操作设计更严格的约束，提升句子简化生成质量
Edit-Constrained Decoding for Sentence Simplification
- 基于编辑操作设计约束，模仿真实简化过程
- 在三个主流数据集上均超越现有方法
- 适合需要高精度句式简化任务的研究者
我们提出一种基于编辑操作的词汇约束解码方法用于句子简化。在句子简化任务中，词汇改写是将复杂句转换为简单句的核心步骤。尽管先前研究已证明词汇约束解码的有效性，但其约束条件较为宽松，可能导致生成效果不佳。为此，我们设计了模仿实际简化过程中执行的编辑操作的约束，并定义了更严格的满足条件。实验结果表明，所提方法在三个常用英语简化语料库上均持续优于已有方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。