1 code implementation • NAACL 2022 • Krishna Sanagavarapu, Jathin Singaraju, Anusha Kakileti, Anirudh Kaza, Aaron Mathews, Helen Li, Nathan Brito, Eduardo Blanco
More importantly, our results demonstrate that existing corpora with synthetic indirect answers to yes-no questions are not beneficial when working with real conversations.
1 code implementation • Findings (NAACL) 2022 • Md Mosharaf Hossain, Luke Holman, Anusha Kakileti, Tiffany Iris Kao, Nathan Raul Brito, Aaron Abraham Mathews, Eduardo Blanco
We first cast the problem of revealing affirmative interpretations from negations as a natural language inference (NLI) classification task.