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 1609.07035cs.CL
收藏

抽象会议摘要的UsingDependency图融合

Abstractive Meeting Summarization UsingDependency Graph Fusion

The Pennsylvania State University(宾夕法尼亚州立大学);Qatar Computing Research Institute(卡塔尔计算研究所);National University of Singapore(新加坡国立大学)

Siddhartha Banerjee, Prasenjit Mitra, Kazunari Sugiyama

摘要:

迄今为止开发的会议会话自动摘要技术主要是提取的,导致摘要不佳。为了改善这一点,我们提出了一种方法来生成抽象的摘要融合重要内容从几个话语。任何会议通常都由几个讨论主题部分组成。对于会议会话中的每个主题段,我们的目标是使用基于整数线性规划的句子融合方法从最重要的话语中生成一个句子摘要。实验结果表明,我们的方法可以产生更多的信息摘要比基线。

英文摘要:

Automatic summarization techniques on meeting conversations developed so far have been primarily extractive, resulting in poor summaries. To improve this, we propose an approach to generate abstractive summaries by fusing important content from several utterances. Any meeting is generally comprised of several discussion topic segments. For each topic segment within a meeting conversation, we aim to generate a one sentence summary from the most important utterances using an integer linear programming-based sentence fusion approach. Experimental results show that our method can generate more informative summaries than the baselines.

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。

↑