arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.01726cs.CL
收藏

一种新的摘要生成与评分方法

A New Approach to Overgenerating and Scoring Abstractive Summaries

University of Central Florida(中佛罗里达大学);Robert Bosch LLC(罗伯特·博世有限责任公司)

Kaiqiang Song, Bingqing Wang, Zhe Feng, Fei Liu

摘要:

提出了一种新的方法,生成内容多样、长度可变的目标摘要的多个变体,然后根据用户的需求进行评分并选择可接受的变体。在单个参考摘要上训练的抽象摘要器可能难以产生实现多个期望属性的输出,即,抓住最重要的信息,忠实于原文,语法和流利。在本文中,我们提出了一个两阶段的策略,产生一个多样化的候选摘要集的源文本在第一阶段,然后评分,并选择在第二阶段的认可。重要的是,我们的生成器可以精确控制摘要的长度,特别适合空间有限的情况。我们的选择器旨在预测最佳摘要长度,并特别强调对原文的忠实性。这两个阶段都可以有效地训练,优化和评估。我们在基准摘要数据集上的实验表明,这种范式可以实现最先进的性能。

英文摘要:

We propose a new approach to generate multiple variants of the target summary with diverse content and varying lengths, then score and select admissible ones according to users' needs. Abstractive summarizers trained on single reference summaries may struggle to produce outputs that achieve multiple desirable properties, i.e., capturing the most important information, being faithful to the original, grammatical and fluent. In this paper, we propose a two-staged strategy to generate a diverse set of candidate summaries from the source text in stage one, then score and select admissible ones in stage two. Importantly, our generator gives a precise control over the length of the summary, which is especially well-suited when space is limited. Our selectors are designed to predict the optimal summary length and put special emphasis on faithfulness to the original text. Both stages can be effectively trained, optimized and evaluated. Our experiments on benchmark summarization datasets suggest that this paradigm can achieve state-of-the-art performance.

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。

↑