Comparative Opinion Summarization via Collaborative Decoding
This addresses the need for better comparison tools in opinion summarization for users choosing between products or services, though it is incremental as it builds on existing summarization tasks.
The paper tackles the problem of generating comparative summaries from multiple sets of reviews to aid decision-making, proposing CoCoSum, which produces higher-quality contrastive and common summaries than state-of-the-art models on the new CoCoTrip benchmark.
Opinion summarization focuses on generating summaries that reflect popular subjective information expressed in multiple online reviews. While generated summaries offer general and concise information about a particular hotel or product, the information may be insufficient to help the user compare multiple different choices. Thus, the user may still struggle with the question "Which one should I pick?" In this paper, we propose the comparative opinion summarization task, which aims at generating two contrastive summaries and one common summary from two different candidate sets of reviews. We develop a comparative summarization framework CoCoSum, which consists of two base summarization models that jointly generate contrastive and common summaries. Experimental results on a newly created benchmark CoCoTrip show that CoCoSum can produce higher-quality contrastive and common summaries than state-of-the-art opinion summarization models. The dataset and code are available at https://github.com/megagonlabs/cocosum