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 2112.07583cs.CL
收藏

一种增强语义对称性的文档摘要方法

Reinforcing Semantic-Symmetry for Document Summarization

Mingyang Song, Liping Jing

摘要:

文档摘要是将一个长文档压缩成一个信息突出、语义描述准确的短文本。主要问题是如何使输出摘要与输入文档在语义上保持一致。为了实现这一目标,最近,研究人员集中在监督端到端的混合方法,其中包含提取器模块和抽象器模块。其中,提取器从输入文档中识别显著句子,并且摘要器从显著句子生成摘要。该模型通过各种策略(例如,强化学习)。在训练混合模型时,存在两个语义间隙(一个是文档和提取的句子之间,另一个是提取的句子和摘要之间)。然而,现有的方法并没有明确地考虑它们,这通常会导致摘要的语义偏差。为了解决上述问题,本文提出了一种新的文档摘要\textbf{e}增强模型-- \textbf{sy}度量学习模型(\textbf{ReSyM}). ReSyM在提取器中引入了语义一致性奖励来弥合第一个差距。语义双重奖励的目的是弥合第二个差距的抽象。整个文档摘要过程通过具有混合奖励机制(结合上述两种奖励)的强化学习来实现。此外,一个全面的句子表示学习方法,提出了充分捕获的信息,从原始文件。在两个广泛使用的基准数据集CNN/Daily Mail和BigPatent上进行了一系列实验。结果显示了ReSyM的优越性,通过比较它与最先进的基线在各种评估指标。

英文摘要:

Document summarization condenses a long document into a short version with salient information and accurate semantic descriptions. The main issue is how to make the output summary semantically consistent with the input document. To reach this goal, recently, researchers have focused on supervised end-to-end hybrid approaches, which contain an extractor module and abstractor module. Among them, the extractor identifies the salient sentences from the input document, and the abstractor generates a summary from the salient sentences. This model successfully keeps the consistency between the generated summary and the reference summary via various strategies (e.g., reinforcement learning). There are two semantic gaps when training the hybrid model (one is between document and extracted sentences, and the other is between extracted sentences and summary). However, they are not explicitly considered in the existing methods, which usually results in a semantic bias of summary. To mitigate the above issue, in this paper, a new \textbf{r}einforcing s\textbf{e}mantic-\textbf{sy}mmetry learning \textbf{m}odel is proposed for document summarization (\textbf{ReSyM}). ReSyM introduces a semantic-consistency reward in the extractor to bridge the first gap. A semantic dual-reward is designed to bridge the second gap in the abstractor. The whole document summarization process is implemented via reinforcement learning with a hybrid reward mechanism (combining the above two rewards). Moreover, a comprehensive sentence representation learning method is presented to sufficiently capture the information from the original document. A series of experiments have been conducted on two wildly used benchmark datasets CNN/Daily Mail and BigPatent. The results have shown the superiority of ReSyM by comparing it with the state-of-the-art baselines in terms of various evaluation metrics.

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。

↑