Towards Effective GANs for Data Distributions with Diverse Modes

no code implementations • ICLR 2018 • Sanchit Agrawal, Gurneet Singh, Mitesh Khapra

(2) The generator (G) is formulated as a continuous function, and the input noise is derived from a connected set, due to which G's output is a connected set.

Leveraging Orthographic Similarity for Multilingual Neural Transliteration

no code implementations • TACL 2018 • Anoop Kunchukuttan, Mitesh Khapra, Gurneet Singh, Pushpak Bhattacharyya

We address the task of joint training of transliteration models for multiple language pairs (multilingual transliteration).

Information Retrieval Multi-Task Learning +1