News

2022

11-Apr Check out our new ACL'22 workshop paper What Language Model to Train if You Have One Million GPU Hours?.
7-Feb Check out our pre-print PromptSource paper.
2-Feb Check out my recent talk on T0++ paper.

2021

19-Jan Our paper T0++ got accepted as a spotlight paper at ICLR'22
15-Oct Our paper Multitask Prompted Training Enables Zero-Shot Task Generalization is online. Model (T0++) , Dataset (P3)
22-Sept Check out my Recent talk on Finetuned Language Models Are Zero-Shot Learners at NTU-NLP lab.
25-Aug My internship work from Amazon got accepted as a short paper in EMNLP.
3-May Two paper UXLA (in main conference) and AugVic (in findings) got accepted in ACL-IJCNLP-2021 .

2020

6-Nov Get back to the PhD study after completing my internship with Amazon Lex Team.
15-Oct Our paper LNMap is accepted in EMNLP-2020.
03-Aug I will be starting my internship at Amazon, with Lex Team.
28-Aug Passed my PhD Qualifying Examination (QE).
28-Apr Preprint of our new paper LNMap released in Arxiv.
24-Apr Preprint of our new paper MultiMix released in Arxiv.
25-Mar Gave a talk on mBART (paper ) in NTU-NLP.
13-Feb Presenting our Cross-lingual-NER paper on AAAI-2020.
4-Jan Got AAAI-2020 travel scholarship. See you in New York.

2019

9-Nov I will be a Teaching Assistant, for Graduate Deep Learning Course of NLP , NTU
11-Nov A paper accepted on AAAI 2020.
15-Jun A paper accepted on ACL 2019.
25-Jan Shows MT system to industry and government stakeholders.
15-Jan Joins NTU-NLP lab as a PhD student.

Skills

Deep Learning, Algorithms and Data structure

Python

Language

C/C++

Language

Experience

 
 
 
 
 
July 1, 2021 – January 28, 2022
East Palo Alto, CA (WFH)

Applied Scientist Intern (Part Time)

Lex Team, Amazon Web Services, Inc.

Cross-lingual Transfer learning under low resource and low parameter scenario.
 
 
 
 
 
August 3, 2020 – November 6, 2020
East Palo Alto, CA (WFH)

Applied Scientist Intern

Lex Team, Amazon Web Services, Inc.

Doing research on Cross-lingual Lex Bot.
 
 
 
 
 
January 15, 2019 – Present
Singapore

Phd Student

Nanyang Technological University

Doing Low-resource Cross-lingual research in NLP on the basis of Second Language Acquisition (SLA).
 
 
 
 
 
September 15, 2018 – January 6, 2019
Bangladesh

Software Engineering Intern

Aubichol IT Limited

Worked on an early startup where the key responsibility was to design the architecture of sports analytic and Translation System.
 
 
 
 
 
September 15, 2017 – August 27, 2018
Singapore

Research Assistant

Nanyang Technological University

Doing Research on Natural Language Processing.
Responsibilities include:
* Research on MT, NER and Adversarial Training.
* Maintain internal GPU servers
* Maintain group web-site
 
 
 
 
 
June 15, 2017 – September 15, 2017
Bangladesh

Lecturer

Southeast University

Teaching undergradute CS student.
Subject tought:
* Introduction to C
* Algorithms
 
 
 
 
 
November 1, 2015 – December 31, 2015
Bangladesh

Software Engineering Intern

XeonBD

Worked on kernel virtualization and cloud computing.

Projects

*
All Deep Learning Other

Algorithms-Code-Library

C++ implementation of various algorithms.

Malay-English Neural Machine Translation System.

This is a tool to translate an English sentence into Malay and vice versa.

Recent & Upcoming Talks

A talk on T0++ paper.
Feb 7, 2022 4:30 PM — 5:30 PM MICL Lab, Singapore
PDF

This talk summarizes the paper Finetuned Language Models Are Zero-Shot Learners.
Sep 22, 2021 10:30 AM — 11:30 AM MICL Lab, Singapore
PDF

This talk summarizes the paper Language Models are Few-Shot Learners.
May 30, 2021 12:00 PM — 1:00 AM Virtual, Zoom Meeting
PDF
See all talks

Publications

Quickly discover relevant content by filtering publications

The crystallization of modeling methods around the Transformer architecture has been a boon for practitioners. Simple, well-motivated …
Paper

Over 2,000 prompts for roughly 170 datasets are available through PromptSource framework.
PDF Github

T0 shows zero-shot task generalization on English natural language prompts, outperforming GPT-3 on many tasks, while being 16x smaller!
PDF Paper

We propose a trasductive approach for few shot cross-lingual classification.
Paper

We propose AugVic, a data augmentation framework for sequence to sequence model (i.e. NMT) using Language Model.
Paper

We propose UXLA, a novel data augmentation framework for self-supervised learning in zero-resource transfer learning scenarios.
Paper

We propose a novel semi-supervised method to learn cross-lingual word embeddings for BLI.
Paper

We propose a superior model and training method for zero resource transfer of Cross-lingual Named Entity Recognition.
PDF Paper

We propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST). …
PDF Website

This book chapter goes through various aspects of regression and maths behind them.
DOI Website