Summarizing and Exploring Tabular Data in Conversational Search
Summarizing and Exploring Tabular Data in Conversational Search
复制标题
DOI：
10.1145/3397271.3401205
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Shuo Zhang;Zhuyun Dai;K. Balog;Jamie Callan
中科院分区：
文献类型：
--
作者：
Shuo Zhang;Zhuyun Dai;K. Balog;Jamie Callan
表格数据为大部分搜索查询提供了答案。然而，背诵整个结果表在会话搜索系统中是不切实际的。我们建议生成自然语言摘要作为描述表中包含的复杂信息的答案。通过众包实验，我们构建了一个新的面向对话的开放域表摘要数据集。它包括带注释的表摘要，不仅可以回答问题，还可以帮助人们探索表中的其他信息。我们利用该数据集开发自动表汇总系统作为SOTA基线。根据实验结果，我们确定了挑战并指出了该资源将支持的未来研究方向。
Tabular data provide answers to a significant portion of search queries. However, reciting an entire result table is impractical in conversational search systems. We propose to generate natural language summaries as answers to describe the complex information contained in a table. Through crowdsourcing experiments, we build a new conversation-oriented, open-domain table summarization dataset. It includes annotated table summaries, which not only answer questions but also help people explore other information in the table. We utilize this dataset to develop automatic table summarization systems as SOTA baselines. Based on the experimental results, we identify challenges and point out future research directions that this resource will support.