权衡熵和相关度的自动摘要技术研究

生成高质量的文档摘要需要用简约而不丢失信息的描述文档,是自动摘要技术的一大难题。该文认为高质量的文档摘要必须尽量多的覆盖原始文档中的信息,同时尽可能的保持紧凑。从这一角度出发,从文档中抽取出熵和相关度这两组特征用以权衡摘要的信息覆盖率和紧凑性。该文采用基于回归的有监督摘要技术对提取的特征进行权衡,并且采用单文档摘要和多文档摘要进行了系统的实验。实验结果证明对于单文档摘要和多文档摘要,权衡熵和相关度均能有效地提高文档摘要的质量。

Leveraging Entropy and Relevance for Document Summarization

It remains a challenge to generate high-quality summaries that could concisely describe the original document without loss of information. In this paper, we argue that high-quality summaries should be compact while covering as much information in the original document as possible. Encouraged by this idea, we extract entropy and relevance to leverage the coverage and the compactness of summaries. We adopt supervised summarization methods based on regression methods to leverage these two features. Moreover, experiments on single and multiple document summarization show that effectively leveraging entropy and relevance could improve the quality of document summarization.
Key wordsdocument summarization; sentence feature extraction; entropy; relevance