no code implementations • ICCV 2021 • Sarthak Garg, Helisa Dhamo, Azade Farshad, Sabrina Musatian, Nassir Navab, Federico Tombari
Scene graphs, composed of nodes as objects and directed-edges as relationships among objects, offer an alternative representation of a scene that is more semantically grounded than images.
no code implementations • EMNLP (sustainlp) 2020 • Yi-Te Hsu, Sarthak Garg, Yi-Hsiu Liao, Ilya Chatsviorkin
Large Transformer models have achieved state-of-the-art results in neural machine translation and have become standard in the field.
no code implementations • ACL 2019 • Sarthak Garg, Joel Ruben Antony Moniz, Anshu Aviral, Priyatham Bollimpalli
In this work, we propose a novel approach that predicts the relationships between various entities in an image in a weakly supervised manner by relying on image captions and object bounding box annotations as the sole source of supervision.
no code implementations • WS 2019 • Xiangkai Zeng, Sarthak Garg, Rajen Chatterjee, Udhyakumar Nallasamy, Matthias Paulik
Finally, we propose a neural extension for an AL sampling method used in the context of phrase-based MT - Round Trip Translation Likelihood (RTTL).
1 code implementation • IJCNLP 2019 • Sarthak Garg, Stephan Peitz, Udhyakumar Nallasamy, Matthias Paulik
The state of the art in machine translation (MT) is governed by neural approaches, which typically provide superior translation accuracy over statistical approaches.
1 code implementation • ACL 2019 • Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg, Matthew R. Gormley, Graham Neubig
We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) --- a semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.
no code implementations • 20 Apr 2019 • Joel Ruben Antony Moniz, Barun Patra, Sarthak Garg
Deep neural networks have become commonplace in the domain of reinforcement learning, but are often expensive in terms of the number of parameters needed.
no code implementations • 27 Sep 2018 • Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg, Matthew R Gormley, Graham Neubig
We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) --- a novel semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.