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 2205.00548cs.CLcs.IR
收藏

基于信息抽取和压缩的大规模多文档文摘

Large-Scale Multi-Document Summarization with Information Extraction and Compression

Northwestern University(西北大学)

Ning Wang, Han Liu, Diego Klabjan

摘要:

我们开发了一个抽象的摘要框架独立的标记数据的多个异构文档。与现有的多文档摘要方法不同,我们的框架处理讲述不同故事的文档,而不是同一主题的文档。我们还增强了现有的句子融合方法与一个单向的语言模型优先融合的句子概率较高,以提高可读性的目标。最后,我们基于CNN/Daily Mail和NewsRoom数据集构建了总共12个数据集变体,其中每个文档组包含大量不同的文档集合,以评估我们的模型与其他基线系统相比的性能。我们的实验表明,我们的框架优于当前国家的最先进的方法,在这个更通用的设置。

英文摘要:

We develop an abstractive summarization framework independent of labeled data for multiple heterogeneous documents. Unlike existing multi-document summarization methods, our framework processes documents telling different stories instead of documents on the same topic. We also enhance an existing sentence fusion method with a uni-directional language model to prioritize fused sentences with higher sentence probability with the goal of increasing readability. Lastly, we construct a total of twelve dataset variations based on CNN/Daily Mail and the NewsRoom datasets, where each document group contains a large and diverse collection of documents to evaluate the performance of our model in comparison with other baseline systems. Our experiments demonstrate that our framework outperforms current state-of-the-art methods in this more generic setting.

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。

↑