Papers by Abu Ubaida Akash
Can Large Language Models Address Open-Target Stance Detection? (2025.findings-acl)
Copied to clipboard
| Challenge: | Stance detection (SD) identifies a text’s position towards a target, typically labeled as favor, against, or none. |
| Approach: | They introduce Open-Target Stance Detection (OTSD) which aims to determine the position of a text towards a target, typically labeled as favor, against, or none. |
| Outcome: | The proposed model outperforms the only existing task, Target-Stance Extraction (TSE), which benefits from predefined targets. |
XL-HeadTags: Leveraging Multimodal Retrieval Augmentation for the Multilingual Generation of News Headlines and Tags (2024.findings-acl)
Copied to clipboard
| Challenge: | XL-HeadTags is a dataset that includes 20 languages across 6 diverse language families. |
| Approach: | They propose to leverage auxiliary information such as images and captions embedded in news articles to retrieve relevant sentences and utilize instruction tuning with variations to generate both headlines and tags for news articles in a multilingual context. |
| Outcome: | The proposed approach generates headlines and tags in a multilingual context using images and captions embedded in the articles and instruction tuning with variations. |
Shironaam: Bengali News Headline Generation using Auxiliary Information (2023.eacl-main)
Copied to clipboard
| Challenge: | Automated headline generation systems have the potential to assist editors in finding interesting headlines to attract visitors or readers. |
| Approach: | They propose to use Bengali news article-headline pairings with auxiliary data to better model headline generation using pre-trained language models. |
| Outcome: | The proposed model improves on a Bengali news headline generation dataset by 3 to 10 percentage points over baselines. |