Papers by Vikram Pudi
Adversarial Examples for Evaluating Math Word Problem Solvers (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing MWP solvers do not understand language and its relation with numbers, and their accuracy is unclear. |
| Approach: | They propose two methods to generate adversarial attacks to evaluate the robustness of existing MWP solvers. |
| Outcome: | The proposed method reduces the accuracy of existing MWP solvers by over 40% on two benchmark datasets. |
A Strong Baseline for Query Efficient Attacks in a Black Box Setting (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing black box search methods are inefficient as they do not consider the amount of queries required to generate adversarial attacks. |
| Approach: | They propose a query efficient attack strategy to generate plausible adversarial examples on text classification and entailment tasks. |
| Outcome: | The proposed attack reduces query count by 75% across all datasets and target models compared to prior attacks in a limited query setting. |
CitRet: A Hybrid Model for Cited Text Span Retrieval (2022.coling-1)
Copied to clipboard
| Challenge: | Current methods for citing text span retrieval (CTSR) rely on pre-trained off-the-shelf deep learning models like SciBERT. |
| Approach: | They propose a hybrid model for cited text span retrieval that leverages unique semantic and syntactic structural characteristics of scientific documents. |
| Outcome: | The proposed model improves state-of-the-art by 15% on the CLSciSumm shared tasks. |
Practice Makes a Solver Perfect: Data Augmentation for Math Word Problem Solvers (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing Math Word Problem solvers do not generalize well and rely on superficial cues to achieve high performance. |
| Approach: | They propose several data augmentation techniques to increase the size of existing MWP datasets by five folds by deploying them to a benchmark dataset. |
| Outcome: | The proposed methods increase the generalization and robustness of existing solvers by over five percentage points on benchmark datasets. |