Subhabrata Mukherjee

research

∙ 07/05/2023

SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference

Autoregressive large language models (LLMs) have made remarkable progres...

0 Luciano Del Corro, et al. ∙

research

∙ 06/19/2023

Adversarial Robustness of Prompt-based Few-Shot Learning for Natural Language Understanding

State-of-the-art few-shot learning (FSL) methods leverage prompt-based f...

0 Venkata Prabhakara Sarath Nookala, et al. ∙

research

∙ 06/05/2023

Orca: Progressive Learning from Complex Explanation Traces of GPT-4

Recent research has focused on enhancing the capability of smaller model...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/24/2023

GRILL: Grounded Vision-language Pre-training via Aligning Text and Image Regions

Generalization to unseen tasks is an important ability for few-shot lear...

0 Woojeong Jin, et al. ∙

research

∙ 05/03/2023

A Systematic Study of Knowledge Distillation for Natural Language Generation with Pseudo-Target Training

Modern Natural Language Generation (NLG) models come with massive comput...

0 Nitay Calderon, et al. ∙

research

∙ 10/31/2022

AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning

Standard fine-tuning of large pre-trained language models (PLMs) for dow...

0 Yaqing Wang, et al. ∙

research

∙ 10/14/2022

AutoMoE: Neural Architecture Search for Efficient Sparsely Activated Transformers

Neural architecture search (NAS) has demonstrated promising results on i...

1 Ganesh Jawahar, et al. ∙

research

∙ 05/24/2022

AdaMix: Mixture-of-Adapter for Parameter-efficient Tuning of Large Language Models

Fine-tuning large-scale pre-trained language models to downstream tasks ...

0 Yaqing Wang, et al. ∙

research

∙ 04/16/2022

Sparsely Activated Mixture-of-Experts are Robust Multi-Task Learners

Traditional multi-task learning (MTL) methods use dense networks that us...

2 Shashank Gupta, et al. ∙

research

∙ 01/29/2022

AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models

Knowledge distillation (KD) methods compress large models into smaller s...

6 Dongkuan Xu, et al. ∙

research

∙ 11/04/2021

CLUES: Few-Shot Learning Evaluation in Natural Language Understanding

Most recent progress in natural language understanding (NLU) has been dr...

2 Subhabrata Mukherjee, et al. ∙

research

∙ 10/16/2021

What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression

Recent works have focused on compressing pre-trained language models (PL...

13 Mengnan Du, et al. ∙

research

∙ 10/12/2021

LiST: Lite Self-training Makes Efficient Few-shot Learners

We present a new method LiST for efficient fine-tuning of large pre-trai...

9 Yaqing Wang, et al. ∙

research

∙ 09/17/2021

Self-training with Few-shot Rationalization: Teacher Explanations Aid Student in Few-shot NLU

While pre-trained language models have obtained state-of-the-art perform...

17 Meghana Moorthy Bhat, et al. ∙

research

∙ 06/23/2021

Fairness via Representation Neutralization

Existing bias mitigation methods for DNN models primarily work on learni...

5 Mengnan Du, et al. ∙

research

∙ 06/08/2021

XtremeDistilTransformers: Task Transfer for Task-agnostic Distillation

While deep and large pre-trained models are the state-of-the-art for var...

18 Subhabrata Mukherjee, et al. ∙

research

∙ 04/16/2021

MetaXL: Meta Representation Transformation for Low-resource Cross-lingual Learning

The combination of multilingual pre-trained representations and cross-li...

12 Mengzhou Xia, et al. ∙

research

∙ 04/12/2021

Self-Training with Weak Supervision

State-of-the-art deep neural networks require large-scale labeled traini...

81 Giannis Karamanolakis, et al. ∙

research

∙ 10/07/2020

Adaptive Self-training for Few-shot Neural Sequence Labeling

Neural sequence labeling is an important technique employed for many Nat...

4 Yaqing Wang, et al. ∙

research

∙ 06/27/2020

Uncertainty-aware Self-training for Text Classification with Few Labels

Recent success of large-scale pre-trained language models crucially hing...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/26/2020

Learning with Weak Supervision for Email Intent Detection

Email remains one of the most frequently used means of online communicat...

0 Kai Shu, et al. ∙

research

∙ 05/18/2020

Product Insights: Analyzing Product Intents in Web Search

Web search engines are frequently used to access information about produ...

0 Nikitha Rao, et al. ∙

research

∙ 05/05/2020

Smart To-Do : Automatic Generation of To-Do Items from Emails

Intelligent features in email service applications aim to increase produ...

0 Sudipto Mukherjee, et al. ∙

research

∙ 05/02/2020

Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer

Multilingual representations embed words from many languages into a sing...

0 Jieyu Zhao, et al. ∙

research

∙ 04/12/2020

TinyMBERT: Multi-Stage Distillation Framework for Massive Multi-lingual NER

Deep and large pre-trained language models are the state-of-the-art for ...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 10/14/2019

STANCY: Stance Classification Based on Consistency Cues

Controversial claims are abundant in online media and discussion forums....

21 Kashyap Popat, et al. ∙

research

∙ 10/04/2019

Distilling Transformers into Simple Neural Networks with Unlabeled Transfer Data

Recent advances in pre-training huge models on large amounts of text thr...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/15/2019

GhostLink: Latent Network Inference for Influence-aware Recommendation

Social influence plays a vital role in shaping a user's behavior in onli...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 04/12/2019

OpenKI: Integrating Open Information Extraction and Knowledge Bases with Relation Inference

In this paper, we consider advancing web-scale knowledge extraction and ...

0 Dongxu Zhang, et al. ∙

research

∙ 09/17/2018

DeClarE: Debunking Fake News and False Claims using Evidence-Aware Deep Learning

Misinformation such as fake news is one of the big challenges of our soc...

0 Kashyap Popat, et al. ∙

research

∙ 06/01/2018

OpenTag: Open Attribute Value Extraction from Product Profiles

Extraction of missing attribute values is to find values describing an a...

0 Guineng Zheng, et al. ∙

research

∙ 07/26/2017

Probabilistic Graphical Models for Credibility Analysis in Evolving Online Communities

One of the major hurdles preventing the full exploitation of information...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/07/2017

Item Recommendation with Continuous Experience Evolution of Users using Brownian Motion

Online review communities are dynamic as users join and leave, adopt new...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/07/2017

Credible Review Detection with Limited Information using Consistency Analysis

Online reviews provide viewpoints on the strengths and shortcomings of p...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/07/2017

People on Media: Jointly Identifying Credible News and Trustworthy Citizen Journalists in Online Communities

Media seems to have become more partisan, often providing a biased cover...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/06/2017

People on Drugs: Credibility of User Statements in Health Communities

Online health communities are a valuable source of information for patie...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/06/2017

Item Recommendation with Evolving User Preferences and Experience

Current recommender systems exploit user and item similarities by collab...

0 Subhabrata Mukherjee, et al. ∙

research

∙ 05/06/2017

Exploring Latent Semantic Factors to Find Useful Product Reviews

Online reviews provided by consumers are a valuable asset for e-Commerce...

0 Subhabrata Mukherjee, et al. ∙

Subhabrata Mukherjee

Featured Co-authors