no code implementations • EACL 2021 • Yi-Chung Lin, Keh-Yih Su
This paper empirically studies whether BERT can really learn to conduct natural language inference (NLI) without utilizing hidden dataset bias; and how efficiently it can learn if it could.
1 code implementation • NAACL 2018 • Chao-Chun Liang, Yu-Shiang Wong, Yi-Chung Lin, Keh-Yih Su
We introduce MeSys, a meaning-based approach, for solving English math word problems (MWPs) via understanding and reasoning in this paper.
no code implementations • COLING 2016 • Chao-Chun Liang, Shih-Hong Tsai, Ting-Yun Chang, Yi-Chung Lin, Keh-Yih Su
This paper presents a meaning-based statistical math word problem (MWP) solver with understanding, reasoning and explanation.