Disordered-DABS: A Benchmark for Dynamic Aspect-Based Summarization in Disordered Texts

Xiaobo Guo, Soroush Vosoughi


Abstract
Aspect-based summarization has seen significant advancements, especially in structured text. Yet, summarizing disordered, large-scale texts, like those found in social media and customer feedback, remains a significant challenge. Current research largely targets predefined aspects within structured texts, neglecting the complexities of dynamic and disordered environments. Addressing this gap, we introduce Disordered-DABS, a novel benchmark for dynamic aspect-based summarization tailored to unstructured text. Developed by adapting existing datasets for cost-efficiency and scalability, our comprehensive experiments and detailed human evaluations reveal that Disordered-DABS poses unique challenges to contemporary summarization models, including state-of-the-art language models such as GPT-3.5.
Anthology ID:
2024.findings-emnlp.24
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
416–431
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.24
DOI:
Bibkey:
Cite (ACL):
Xiaobo Guo and Soroush Vosoughi. 2024. Disordered-DABS: A Benchmark for Dynamic Aspect-Based Summarization in Disordered Texts. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 416–431, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Disordered-DABS: A Benchmark for Dynamic Aspect-Based Summarization in Disordered Texts (Guo & Vosoughi, Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.24.pdf