Papers by Bonnie J Dorr
DETQUS: Decomposition-Enhanced Transformers for QUery-focused Summarization (2025.naacl-long)
Copied to clipboard
Yasir Khan, Xinlei Wu, Sangpil Youm, Justin Ho, Aryaan Mehboob Shaikh, Jairo Garciga, Rohan Sharma, Bonnie J Dorr
| Challenge: | Query-focused tabular summarization is an emerging task in table-to-text generation . traditional transformer-based approaches face challenges due to token limitations and the complexity of reasoning over large tables. |
| Approach: | They propose a system that leverages tabular decomposition alongside a fine-tuned encoder-decoder model to improve summarization accuracy. |
| Outcome: | a new system outperforms the state-of-the-art REFACTOR model in a Query-focused tabular summarization task . the proposed system achieves a ROUGE-L score of 0.4437, outperforming the previous state- of-the art model . |
FIDELITY: Fine-grained Interpretable Distillation for Effective Language Insights and Topic Yielding (2025.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for topic modeling generate contextually specific and semantically intuitive topics, especially in dynamic environments and low-resource languages. |
| Approach: | They propose a hybrid method that combines topic modeling and text summarization to produce fine-grained, semantically rich, and contextually relevant output. |
| Outcome: | FIDELITY outperforms traditional models in topic diversity, similarity, and ability to process new, unseen documents. |