Domain Adaptation for NMT via Filtered Iterative Back-Translation

no code implementations • EACL (AdaptNLP) 2021 • Surabhi Kumari, Nikhil Jaiswal, Mayur Patidar, Manasi Patwardhan, Shirish Karande, Puneet Agarwal, Lovekesh Vig

In comparison, in this work, we observe that a simpler filtering approach based on a domain classifier, applied only to the pseudo-training data can consistently perform better, providing performance gains of 1. 40, 1. 82 and 0. 76 in terms of BLEU score for Medical, Law and IT in one direction, and 1. 28, 1. 60 and 1. 60 in the other direction in low resource scenario over competitive baselines.

Domain Adaptation Machine Translation +2

Improving NMT via Filtered Back Translation

no code implementations • AACL (WAT) 2020 • Nikhil Jaiswal, Mayur Patidar, Surabhi Kumari, Manasi Patwardhan, Shirish Karande, Puneet Agarwal, Lovekesh Vig

This is further followed by fine-tuning on the domain-specific corpus.

Document Level Machine Translation Machine Translation +3

Neural Sarcasm Detection using Conversation Context

no code implementations • WS 2020 • Nikhil Jaiswal

We experiment with a variety of PLRMs either on the twitter utterance in isolation or utilizing the contextual information along with the utterance.

Sarcasm Detection