A Character-Level Length-Control Algorithm for Non-Autoregressive Sentence Summarization

Puyuan Liu, Xiang Zhang, Lili Mou

Keywords: summarization, non-autoregressive generation, length control

TL;DR: We propose a Non-Autoregressive summarization model with Character-level length Control (NACC) approach, which not only can control the number of characters in the model output explicitly but also is efficient in inference.

Abstract: 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.