University of Cambridge > Talks.cam > NLIP Seminar Series > Understanding Comparative Questions and Retrieving Argumentative Answers

Understanding Comparative Questions and Retrieving Argumentative Answers

Add to your list(s) Download to your calendar using vCal

  • UserAlexander Bondarenko, University of Leipzig
  • ClockFriday 08 March 2024, 12:00-13:00
  • HouseComputer Lab, SS03.

If you have a question about this talk, please contact Richard Diehl Martinez.

In this talk, Alexander will cover from different perspectives how search systems can respond to comparative questions, which was the main focus of his PhD studies. He will discuss approaches to identifying comparative questions and identifying important constituents of comparative questions, such as the options being compared. Then, Alexander will cover stance detection of answers towards these comparison options. Following that, he will discuss argument retrieval, which represents a specific case within the broader domain of information retrieval. In the final part, Alexander will provide a brief overview of his current project, which involves the development of a chatbot in the field of infectious diseases.

Bio:

Alexander is a postdoc at the Medical Faculty at Leipzig University. During his PhD at the Martin Luther University Halle-Wittenberg and the Friedrich Schiller University Jena, Alexander worked on the topics concerning answering comparative questions with arguments. In particular, he focused on question understanding, argument retrieval, argument quality prediction, and stance detection. His current research focuses on a generative AI system in the domain of infectious diseases that is powered by information retrieval (RAG). Alexander regularly serves as a program committee member for different IR conferences such as CHIIR , ECIR, and CLEF . He was also a lead organizer of Touché, a series of scientific events, and shared tasks on computational argumentation and causality.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity