Informative and Controllable Opinion Summarization
This addresses the need for more informative and customizable opinion summaries for users dealing with large review sets, though it is incremental as it builds on existing neural methods.
The paper tackles the problem of information loss in two-stage opinion summarization by proposing a framework that uses all input reviews via dense vector condensation, resulting in more informative summaries and effective customization, with state-of-the-art improvements on the Rotten Tomatoes dataset.
Opinion summarization is the task of automatically generating summaries for a set of reviews about a specific target (e.g., a movie or a product). Since the number of reviews for each target can be prohibitively large, neural network-based methods follow a two-stage approach where an extractive step first pre-selects a subset of salient opinions and an abstractive step creates the summary while conditioning on the extracted subset. However, the extractive model leads to loss of information which may be useful depending on user needs. In this paper we propose a summarization framework that eliminates the need to rely only on pre-selected content and waste possibly useful information, especially when customizing summaries. The framework enables the use of all input reviews by first condensing them into multiple dense vectors which serve as input to an abstractive model. We showcase an effective instantiation of our framework which produces more informative summaries and also allows to take user preferences into account using our zero-shot customization technique. Experimental results demonstrate that our model improves the state of the art on the Rotten Tomatoes dataset and generates customized summaries effectively.