Edit-Constrained Decoding for Sentence Simplification
This work addresses sentence simplification for NLP applications, but it is incremental as it builds on existing lexically constrained decoding approaches.
The authors tackled the problem of sub-optimal generation in sentence simplification by designing stricter edit-based constraints for decoding, resulting in consistent performance improvements over previous methods on three English corpora.
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.