A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization
This addresses a specific gap in summarization for applications like headline generation, but it is incremental as it builds on existing non-autoregressive methods.
The paper tackles the problem of explicit character-level length control in sentence summarization, proposing a dynamic programming algorithm based on the Connectionist Temporal Classification model, which results in higher ROUGE scores and more complete sentences.
Sentence summarization aims at compressing a long sentence into a short one that keeps the main gist, and has extensive real-world applications such as headline generation. In previous work, researchers have developed various approaches to improve the ROUGE score, which is the main evaluation metric for summarization, whereas controlling the summary length has not drawn much attention. In our work, we address a new problem of explicit character-level length control for summarization, and propose a dynamic programming algorithm based on the Connectionist Temporal Classification (CTC) model. Results show that our approach not only achieves higher ROUGE scores but also yields more complete sentences.