arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2205.14522cs.CLcs.LG
收藏

一种非自回归句子自动摘要的分级长度控制算法

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

Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所);University of Alberta(阿尔伯塔大学)

Puyuan Liu, Xiang Zhang, Lili Mou

摘要:

摘要的目的是将一个长句压缩成一个简短的句子,并保持主旨,并有广泛的实际应用,如标题生成。在以前的工作中,研究人员已经开发了各种方法来提高ROUGE分数,这是摘要的主要评价指标,而控制摘要长度并没有引起太多的关注。在我们的工作中,我们解决了一个新的问题,显式字符级长度控制摘要,并提出了一个动态规划算法的基础上的连接主义时间分类(CTC)模型。实验结果表明,我们的方法不仅取得了更高的ROUGE分数,但也产生更多的完整的句子。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑