InfoTabS - Inference on Tables as Semi-Structured Data

September 20, 2020

Speaker: Vivek Gupta, Y11 Dual-Degree CSE, 1st Co-ordinator of SIGML, Currently PhD student at School of Computiong, University of Utah.
Title: InfoTabS - Inference on Tables as Semi-Structured Data
Type: Own PhD Research
Other memebrs: Maitrey Mehta, Pegah Nokhiz, Vivek Srikumar
Understanding ubiquitous semi-structured tabulated data requires not only comprehending the meaning of text fragments, but also implicit relationships between them. We argue that such data can prove as a testing ground for understanding how we reason about information. To study this, we introduce a new dataset called INFOTABS, consisting of human-written textual hypotheses based on premises that are tables extracted from Wikipedia info-boxes. Our analysis shows that the semi-structured, multi-domain and heterogeneous nature of the premises admits complex, multi-faceted reasoning.

He has also shared many of his experiences and some valuable insights for heading into research as a career option.

Slide: Link
Video: Youtube

Connect with the Speaker on -