Web: http://arxiv.org/abs/2112.08777

May 9, 2022, 1:11 a.m. | Avi Caciularu, Ido Dagan, Jacob Goldberger, Arman Cohan

cs.CL updates on arXiv.org arxiv.org

Long-context question answering (QA) tasks require reasoning over a long
document or multiple documents. Addressing these tasks often benefits from
identifying a set of evidence spans (e.g., sentences), which provide supporting
evidence for answering the question. In this work, we propose a novel method
for equipping long-context QA models with an additional sequence-level
objective for better identification of the supporting evidence. We achieve this
via an additional contrastive supervision signal in finetuning, where the model
is encouraged to explicitly discriminate …

arxiv context learning question answering

Data Analyst, Patagonia Action Works

@ Patagonia | Remote

Data & Insights Strategy & Innovation General Manager

@ Chevron Services Company, a division of Chevron U.S.A Inc. | Houston, TX

Faculty members in Research areas such as Bayesian and Spatial Statistics; Data Privacy and Security; AI/ML; NLP; Image and Video Data Analysis

@ Ahmedabad University | Ahmedabad, India

Director, Applied Mathematics & Computational Research Division

@ Lawrence Berkeley National Lab | Berkeley, Ca

Business Data Analyst

@ MainStreet Family Care | Birmingham, AL

Assistant/Associate Professor of the Practice in Business Analytics

@ Georgetown University McDonough School of Business | Washington DC