Decomposed Opinion Summarization with Verified Aspect-Aware Modules
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913864755445760 |
|---|---|
| author | Li, Miao Lau, Jey Han Hovy, Eduard Lapata, Mirella |
| author_facet | Li, Miao Lau, Jey Han Hovy, Eduard Lapata, Mirella |
| contents | Opinion summarization plays a key role in deriving meaningful insights from large-scale online reviews. To make the process more explainable and grounded, we propose a domain-agnostic modular approach guided by review aspects (e.g., cleanliness for hotel reviews) which separates the tasks of aspect identification, opinion consolidation, and meta-review synthesis to enable greater transparency and ease of inspection. We conduct extensive experiments across datasets representing scientific research, business, and product domains. Results show that our approach generates more grounded summaries compared to strong baseline models, as verified through automated and human evaluations. Additionally, our modular approach, which incorporates reasoning based on review aspects, produces more informative intermediate outputs than other knowledge-agnostic decomposition approaches. Lastly, we provide empirical results to show that these intermediate outputs can support humans in summarizing opinions from large volumes of reviews. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_17191 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decomposed Opinion Summarization with Verified Aspect-Aware Modules Li, Miao Lau, Jey Han Hovy, Eduard Lapata, Mirella Computation and Language Information Retrieval Opinion summarization plays a key role in deriving meaningful insights from large-scale online reviews. To make the process more explainable and grounded, we propose a domain-agnostic modular approach guided by review aspects (e.g., cleanliness for hotel reviews) which separates the tasks of aspect identification, opinion consolidation, and meta-review synthesis to enable greater transparency and ease of inspection. We conduct extensive experiments across datasets representing scientific research, business, and product domains. Results show that our approach generates more grounded summaries compared to strong baseline models, as verified through automated and human evaluations. Additionally, our modular approach, which incorporates reasoning based on review aspects, produces more informative intermediate outputs than other knowledge-agnostic decomposition approaches. Lastly, we provide empirical results to show that these intermediate outputs can support humans in summarizing opinions from large volumes of reviews. |
| title | Decomposed Opinion Summarization with Verified Aspect-Aware Modules |
| topic | Computation and Language Information Retrieval |
| url | https://arxiv.org/abs/2501.17191 |