Conference Publications

Measuring Retrieval Complexity in Question Answering Systems

Matteo Gabburo, Nicolaas Jedema, Siddhant Garg, Leonardo Ribeiro, Alessandro Moschitti
ACL 2024 Findings
[Paper]

Towards Improved Multi-Source Attribution for Long-Form Answer Generation

Nilay Patel, Shivashankar Subramanian, Siddhant Garg, Pratyay Banerjee, Amita Misra
NAACL 2024
[Paper]

ProMISe: A Proactive Multi-turn Dialogue Dataset for Information-seeking Intent Resolution

Yash Butala, Siddhant Garg, Pratyay Banerjee, Amita Misra
EACL 2024 Findings
[Paper]

SQUARE: Automatic Question Answering Evaluation using Multiple Positive and Negative References

Matteo Gabburo, Siddhant Garg, Rik Koncel-Kedziorski, Alessandro Moschitti
IJCNLP-AACL 2023 (Oral Presentation)
[Paper]

Learning Answer Generation using Supervision from Automatic Question Answering Evaluators

Matteo Gabburo, Siddhant Garg, Rik Koncel-Kedziorski, Alessandro Moschitti
ACL 2023
[Paper] [Slides]

Context-Aware Transformer Pre-Training for Answer Sentence Selection

Luca Di Liello, Siddhant Garg, Alessandro Moschitti
ACL 2023
[Paper]

Knowledge Transfer from Answer Ranking to Answer Generation

Matteo Gabburo, Rik Koncel-Kedziorski, Siddhant Garg, Luca Soldaini, Alessandro Moschitti
EMNLP 2022
[Paper] [Poster]

Pre-training Transformer Models with Sentence-Level Objectives for Answer Sentence Selection

Luca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro Moschitti
EMNLP 2022
[Paper] [Poster]

Paragraph-based Transformer Pretraining for Multi-Sentence Inference

Luca Di Liello, Siddhant Garg, Luca Soldaini, Alessandro Moschitti
NAACL 2022
[Paper] [Code] [Poster]

Will this Question be Answered? Question Filtering via Answer Model Distillation for Efficient Question Answering

Siddhant Garg, Alessandro Moschitti
EMNLP 2021 (Oral Presentation)
[Paper] [Slides] [Video] [Poster]

Towards Robustness to Label Noise in Text Classification via Noise Modeling

Siddhant Garg*, Goutham Ramakrishnan* , Varun Thumbe*
CIKM 2021
ICLR 2021 RobustML Workshop, S2D-OLAD Workshop
[Paper] [Code] [Slides] [Video] [Poster]

Functional Regularization for Representation Learning: A Unified Theoretical Perspective

Siddhant Garg, Yingyu Liang
NeurIPS 2020
[Paper] [Video] [Slides] [Code] [Poster]

BAE: BERT-based Adversarial Examples for Text Classification

Siddhant Garg*, Goutham Ramakrishnan*
EMNLP 2020
[Paper] [Blog] [Slides] [Video] [Code]

Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer

Siddhant Garg, Rohit Kumar Sharma, Yingyu Liang
AACL-IJCNLP 2020
[Paper] [Video] [Slides]

Can Adversarial Weight Perturbations Inject Neural Backdoors?

Siddhant Garg*, Adarsh Kumar*, Vibhor Goel*, Yingyu Liang
CIKM 2020
[Paper] [Code] [Video]

TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection

Siddhant Garg, Thuy Vu, Alessandro Moschitti
AAAI 2020 (Oral Presentation)
[Paper] [Code] [Slides] [Blog] [Poster]

Stochastic Bandits with Delayed Composite Anonymous Feedback

Siddhant Garg*, Aditya Kumar Akash*
NeurIPS 2019 Workshop on ML with Guarantees
[Paper] [Poster]

Interpretable Inference Graphs for Face Recognition

Siddhant Garg*, Goutham Ramakrishnan*, Varun Thumbe
IVCNZ 2019
[Paper] [Poster] [Slide]

Surprisingly Easy Hard-Attention for Sequence to Sequence Learning

Shiv Shankar*, Siddhant Garg*, Sunita Sarawagi
EMNLP 2018 (Oral Presentation)
[Paper] [Code] [Video] [Slides]

Journal Publications

An Analysis of Attentive Walk-Aggregating Graph Neural Networks

Mehmet F. Demirel, Shengchao Liu, Siddhant Garg, Yingyu Liang , 2021
Transactions on Machine Learning Research (TMLR) 2022
[Paper] [Code]

Pre-Prints

Advances in Quantum Deep Learning: An Overview

Siddhant Garg*, Goutham Ramakrishnan* , 2020
[Paper]

Data Ordering Patterns for Neural Machine Translation: An Empirical Study

Siddhant Garg , 2019
[Paper]

Theses

Understanding Representation Learning Paradigms with Applications to Low Resource Text Classification

Master’s Thesis, University of Wisconsin-Madison, 2020
Advisor: Yingyu Liang
[Thesis]

Structured Attention Sequence to Sequence Models

Bachelor’s Thesis, IIT Bombay, 2018
Advisor: Sunita Sarawagi
[Thesis] [Slides]

Teaching

[Fall 2018] CS540: Artificial Intelligence, Jerry Zhu, UW Madison
[Spring’18] CS101: Introduction to Computer Programming, Krishna S, IIT Bombay
[Fall 2017] CS305 + 341: Computer Architecture, Bhaskaran Raman, IIT Bombay
[Fall 2016] CS215: Data Analysis and Interpretation, Suyash Awate, IIT Bombay
[Fall 2015] BB101: Introduction to Biology, Soumyo Mukherjee, IIT Bombay

Academic Service

Served as an Area Chair (AC) for the following conferences:
2024: EACL (Question Answering Track)
2023: EMNLP (Question Answering Track)

Served as a reviewer for the following journals in the year:
2021: JAIR, IEEE TNNLS

Served as a reviewer for the following conferences:
2024: NAACL
2023: ICLR, ICML, ACL, NeurIPS, EMNLP
2022: ICLR, ACL, NAACL, NeurIPS, EMNLP
2021: AAAI , NAACL, ICML (Top 10% of Reviewers) , ACL (Outstanding Reviewer), SIGIR, EMNLP, NeurIPS
2020: AAAI, ACL , ESANN, EMNLP (Outstanding Reviewer) , NeurIPS (Top 10% of Reviewers)
2019: EMNLP