Papers by Abhilash Nandy
CLMSM: A Multi-Task Learning Framework for Pre-training on Procedural Text (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to solve procedural reasoning tasks are limited by the prior art. |
| Approach: | They propose a domain-specific, continual pre-training framework that learns from a large set of procedural recipes. |
| Outcome: | The proposed framework outperforms baselines on recipes (in-domain) but is able to generalize to open-domain procedural NLP tasks. |
Order-Based Pre-training Strategies for Procedural Text Understanding (2024.naacl-short)
Copied to clipboard
| Challenge: | Procedural text is difficult to understand due to the changing attributes of entities in the context. |
| Approach: | They propose sequence-based pre-training methods to enhance procedural understanding in natural language processing by using ordered instructions to guide individuals through a task. |
| Outcome: | The proposed methods improve on two datasets in the datasets NPN-Cooking and ProPara domains respectively. |
***YesBut***: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models (2024.emnlp-main)
Copied to clipboard
Abhilash Nandy, Yash Agarwal, Ashish Patwa, Millon Das, Aman Bansal, Ankit Raj, Pawan Goyal, Niloy Ganguly
| Challenge: | Existing Vision-Language models perform poorly on satirical image detecting tasks . satire and humor are powerful tools to highlight issues, provoke thought, and encourage critical perspective . |
| Approach: | They propose to use a dataset to evaluate satirical images and satire images to detect satiric images . they also propose to generate the reason behind the image being satiral by generating one half of the image to be satisfying . |
| Outcome: | The proposed dataset contains 2547 images, 1084 satirical and 1463 non-satirically, with different artistic styles. |
A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing research focuses on simple queries with a single intent, lacking effective systems for handling complex queries with multiple intents. |
| Approach: | They propose a multi-label multi-class intent detection dataset curated from existing benchmarks and a pointer network-based architecture to extract intent spans and detect multiple intents with coarse and fine-grained labels in the form of sextuplets. |
| Outcome: | The proposed system outperforms baseline approaches in terms of accuracy and F1-score. |
An Evaluation Framework for Legal Document Summarization (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing metrics for summarizing legal documents fail to evaluate intent in the original text. |
| Approach: | They propose an automated intent-based summarization metric which shows a better agreement with human evaluation as compared to other automated metrics like BLEU, ROUGE-L etc. |
| Outcome: | The proposed method shows that human evaluation is more accurate than other metrics. |
Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs (2025.acl-short)
Copied to clipboard
| Challenge: | Large language models require fine-tuning, which is computationally expensive and challenging. |
| Approach: | They propose a method that generates soft prompts based on input tokens and attends different tokens with varying importance. |
| Outcome: | The proposed method is simple and efficient, keeping the number of trainable parameters small. |
Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework (2021.findings-emnlp)
Copied to clipboard
| Challenge: | EMQAP is an automated question answering system for electronics devices . it uses a supervised multitask learning framework to identify the section in the E-manual where the answer can be found and the exact answer span within that section. |
| Approach: | They develop an algorithm to exploit data from E-manuals and pretrain RoBERTa on it. |
| Outcome: | The proposed algorithm improves ROUGE-L F1 scores over most competitive baseline. |