A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge

ACL 2018

A Generalized Knowledge Hunting Framework for the Winograd Schema Challenge

Jun 29, 2018
|
96 views
Details
Abstract: We introduce an automatic system that performs well on two common-sense reasoning tasks, the Winograd Schema Challenge (WSC) and the Choice of Plausible Alternatives (COPA). Problem instances from these tasks require diverse, complex forms of inference and knowledge to solve. Our method uses a knowledge-hunting module to gather text from the web, which serves as evidence for candidate problem resolutions. Given an input problem, our system generates relevant queries to send to a search engine. It extracts and classifies knowledge from the returned results and weighs it to make a resolution. Our approach improves F1 performance on the WSC by 0.16 over the previous best and is competitive with the state-of-the-art on COPA, demonstrating its general applicability. Authors: Ali Emami, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung (McGill University, Maluuba Research)

Comments
loading...