I will introduce a recent research project on natural language inference (NLI): incorporating knowledge for NLI and its application - finding counterevidence of a given sentence (EMNLP 2021 Findings). Finding counterevidence to statements is key to many tasks, including counterargument generation. We build a system that, given a statement, retrieves counterevidence from diverse sources on the Web. At the core of this system is a NLI model that determines whether a candidate sentence is valid counterevidence or not. Most NLI models to date, however, lack proper reasoning abilities necessary to find counterevidence that involves complex inference. Thus, we present a knowledge-enhanced NLI model that aims to handle causality- and example-based inference by incorporating knowledge graphs. Our NLI model outperforms baselines for NLI tasks, especially for instances that require the targeted inference. In addition, this NLI model further improves the counterevidence retrieval system, notably finding complex counterevidence better.

온라인줌 링크: https://snu-ac-kr.zoom.us/j/83163353923

JinYeong Bak is an assistant professor in the colleague of computing at Sungkyunkwan University. His research interests are analyzing human behaviors from their conversations and building open-domain conversation models from the insights of the analysis. He worked at Microsoft Research Asia as a research intern and United Nations Global Pulse Lab Jakarta as a junior data scientist. He received Ph.D. and M.S. from the KAIST and a B.S. from Sungkyunkwan University. His research has been published in ACL, EMNLP, CHI, and ICWSM. His personal homepage: https://nosyu.kr and lab homepage: https://hli.skku.edu