Content Selection in Deep Learning Models of Summarization
Content Selection in Deep Learning Models of Summarization
复制标题
DOI：
10.18653/v1/d18-1208
复制
发表时间：
2018-10
期刊：
影响因子：
--
通讯作者：
Chris Kedzie;K. McKeown;Hal Daumé
中科院分区：
文献类型：
--
作者：
Chris Kedzie;K. McKeown;Hal Daumé
我们在新闻、个人故事、会议和医学文章等领域进行了深度学习摘要模型的实验，以了解内容选择是如何进行的。我们发现，许多先进的提取摘要的国家复杂的功能并没有提高性能比简单的模型。这些结果表明，为新领域创建摘要器比以前的工作更容易，并质疑深度学习模型对具有大量数据集的领域（即，news）。与此同时，他们提出了总结新研究的重要问题;即，需要更适合总结任务的新形式的句子表示或外部知识来源。
We carry out experiments with deep learning models of summarization across the domains of news, personal stories, meetings, and medical articles in order to understand how content selection is performed. We find that many sophisticated features of state of the art extractive summarizers do not improve performance over simpler models. These results suggest that it is easier to create a summarizer for a new domain than previous work suggests and bring into question the benefit of deep learning models for summarization for those domains that do have massive datasets (i.e., news). At the same time, they suggest important questions for new research in summarization; namely, new forms of sentence representations or external knowledge sources are needed that are better suited to the sumarization task.