Papers with MAST
MAST: A Multi-View Alignment Strategy for Optimal Transport-Based Contrastive Clustering of Short Text (2026.findings-acl)
Copied to clipboard
| Challenge: | Short text clustering has gained significant prominence due to its ubiquity in real-world applications. |
| Approach: | They propose a multi-view alignment strategy with transport-based clustering that integrates structural views to capture multi-granularity semantic features. |
| Outcome: | Experiments show that MAST outperforms state-of-the-art methods on benchmark datasets. |
The Multimodal Annotation Software Tool (MAST) (2022.lrec-1)
Copied to clipboard
| Challenge: | Existing visual and multimodal annotation systems are limited in scope and applicability. |
| Approach: | They propose a tool that allows users to analyze visual and multimodal documents . they aim to provide a powerful and innovative annotation tool with application across fields . |
| Outcome: | The MAST tool allows users to analyze visual and multimodal documents . it allows annotation theories to be citable, while evolving and being shared . |