Decomposed Opinion Summarization with Verified Aspect-Aware Modules
This work addresses the need for transparent and inspectable opinion summarization for users analyzing large-scale online reviews, representing an incremental improvement with a modular design.
The paper tackled the problem of making opinion summarization more explainable and grounded by proposing a domain-agnostic modular approach that separates aspect identification, opinion consolidation, and meta-review synthesis, resulting in more grounded summaries compared to strong baselines as verified through automated and human evaluations.
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.