no code implementations • 2 Feb 2020 • Rupam Patir, Shubham Singhal, C. Anantaram, Vikram Goyal
Different deep learning models built on the same training data may capture different views of the data based on the underlying techniques used.
no code implementations • 26 Nov 2018 • Aishwarya Chhabra, Pratik Saini, Amit Sangroya, C. Anantaram
Our latent belief identification approach shows an accuracy of 87% and this results in efficient and meaningful dialog management.
no code implementations • 12 Oct 2017 • C. Anantaram, Sunil Kumar Kopparapu
However, when such engines are used for specific domains, they may not recognize domain-specific words well, and may produce erroneous output.