157 citations · 618 across the 30 of their papers we have counts for
33 papers
Impact of Visual Context on Noisy Multimodal NMT: An Empirical Study for English to Indian Languages
Baban Gain, Dibyanayan Bandyopadhyay, Samrat Mukherjee +2
Neural Machine Translation (NMT) has made remarkable progress using large-scale textual data, but the potential of incorporating multimodal inputs, especially visual information, r…
XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation
Subhabrata Mukherjee, Ahmed Hassan Awadallah, Jianfeng Gao
While deep and large pre-trained models are the state-of-the-art for various natural language processing tasks, their huge size poses significant challenges for practical uses in r…
MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning
Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee +3
The combination of multilingual pre-trained representations and cross-lingual transfer learning is one of the most effective methods for building functional NLP systems for low-res…
Self-Training with Weak Supervision
Giannis Karamanolakis, Subhabrata Mukherjee, Guoqing Zheng +1
State-of-the-art deep neural networks require large-scale labeled training data that is often expensive to obtain or not available for many tasks. Weak supervision in the form of d…
Adaptive Self-training for Few-shot Neural Sequence Labeling
Yaqing Wang, Subhabrata Mukherjee, Haoda Chu +4
Sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and s…
Uncertainty-aware Self-training for Text Classification with Few Labels
Subhabrata Mukherjee, Ahmed Hassan Awadallah
Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive…