[05-23] Data-To-Text: Generating Textual Summaries of Complex Data

文章来源:  |  发布时间:2018-05-23  |  【打印】 【关闭


  Title:  Data-To-Text: Generating Textual Summaries of Complex Data

  Speaker:  Prof.Ehud Reiter(University of Aberdeen)

  Time:  2018年5月23日星期三 上午10:00

  Venue: 中科院软件所五号楼4层第一会议室


  Abstract: Data-to-Text systems use Natural Language Generation (NLG) technology to generate summaries in English (and other human languages) of complex non-linguistic (usually numeric) data sets. In my talk, I will give a general introduction to data-to-text, including examples of systems and applications, current technology and evaluations, and an overview of commercial activity in this area. I will also briefly summarise some of the current research in my group on improving data-to-text technology.


  Biography: Ehud Reiter is a Professor of Computing Science at the University of Aberdeen (UK), and also Chief Scientist of Arria NLG, which evolved from a spinout company he set up in 2009. He has worked on Natural Language Generation for the past 30 years, and is one of the most cited authors in NLG (with a Google Scholar h-index of 38), as well as the author of the most popular NLG textbook and creator of the most popular open——source NLG software package (simplenlg). For more information about Prof Reiter, see ehudreiter.com