Sparsh Gupta


2019

pdf bib
Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks
Anush Kamath | Sparsh Gupta | Vitor Carvalho
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Adversarial domain adaptation has been recently proposed as an effective technique for textual matching tasks, such as question deduplication. Here we investigate the use of gradient reversal on adversarial domain adaptation to explicitly learn both shared and unshared (domain specific) representations between two textual domains. In doing so, gradient reversal learns features that explicitly compensate for domain mismatch, while still distilling domain specific knowledge that can improve target domain accuracy. We evaluate reversing gradients for adversarial adaptation on multiple domains, and demonstrate that it significantly outperforms other methods on question deduplication as well as on recognizing textual entailment (RTE) tasks, achieving up to 7% absolute boost in base model accuracy on some datasets.

pdf bib
On Committee Representations of Adversarial Learning Models for Question-Answer Ranking
Sparsh Gupta | Vitor Carvalho
Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019)

Adversarial training is a process in Machine Learning that explicitly trains models on adversarial inputs (inputs designed to deceive or trick the learning process) in order to make it more robust or accurate. In this paper we investigate how representing adversarial training models as committees can be used to effectively improve the performance of Question-Answer (QA) Ranking. We start by empirically probing the effects of adversarial training over multiple QA ranking algorithms, including the state-of-the-art Multihop Attention Network model. We evaluate these algorithms on several benchmark datasets and observe that, while adversarial training is beneficial to most baseline algorithms, there are cases where it may lead to overfitting and performance degradation. We investigate the causes of such degradation, and then propose a new representation procedure for this adversarial learning problem, based on committee learning, that not only is capable of consistently improving all baseline algorithms, but also outperforms the previous state-of-the-art algorithm by as much as 6% in NDCG.