1 code implementation • 23 Sep 2020 • Ananya B. Sai, Akash Kumar Mohankumar, Siddhartha Arora, Mitesh M. Khapra
However, no such data is publicly available, and hence existing models are usually trained using a single relevant response and multiple randomly selected responses from other contexts (random negatives).
no code implementations • NAACL 2019 • Siddhartha Arora, Mitesh M. Khapra, Harish G. Ramaswamy
In order to overcome this, we use standard simple models which do not capture all pairwise interactions, but learn to emulate certain characteristics of a complex teacher network.
1 code implementation • EMNLP 2018 • Nikita Moghe, Siddhartha Arora, Suman Banerjee, Mitesh M. Khapra
Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them.
no code implementations • COLING 2018 • Suman Banerjee, Nikita Moghe, Siddhartha Arora, Mitesh M. Khapra
("Can you help me in booking a table at this restaurant?").