TY - GEN
T1 - Knowledge-Enhanced Evidence Retrieval for Counterargument Generation
AU - Jo, Yohan
AU - Yoo, Haneul
AU - Bak, Jinyeong
AU - Oh, Alice
AU - Reed, Chris
AU - Hovy, Eduard
N1 - Publisher Copyright:
© 2021 Association for Computational Linguistics.
PY - 2021
Y1 - 2021
N2 - 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 natural language inference (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.
AB - 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 natural language inference (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.
UR - https://www.scopus.com/pages/publications/85128538303
U2 - 10.18653/v1/2021.findings-emnlp.264
DO - 10.18653/v1/2021.findings-emnlp.264
M3 - Conference contribution
AN - SCOPUS:85128538303
T3 - Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021
SP - 3074
EP - 3094
BT - Findings of the Association for Computational Linguistics, Findings of ACL
A2 - Moens, Marie-Francine
A2 - Huang, Xuanjing
A2 - Specia, Lucia
A2 - Yih, Scott Wen-Tau
PB - Association for Computational Linguistics (ACL)
T2 - 2021 Findings of the Association for Computational Linguistics, Findings of ACL: EMNLP 2021
Y2 - 7 November 2021 through 11 November 2021
ER -