Extractive Opinion Summarization in Quantized Transformer Spaces
This work addresses the problem of summarizing opinions from numerous reviews for users interested in understanding popular and aspect-specific sentiments.
The paper introduces Quantized Transformer (QT), an unsupervised system for extractive opinion summarization that identifies popular opinions from hundreds of reviews. It also enables controllable, aspect-specific summarization without additional training.
We present the Quantized Transformer (QT), an unsupervised system for extractive opinion summarization. QT is inspired by Vector-Quantized Variational Autoencoders, which we repurpose for popularity-driven summarization. It uses a clustering interpretation of the quantized space and a novel extraction algorithm to discover popular opinions among hundreds of reviews, a significant step towards opinion summarization of practical scope. In addition, QT enables controllable summarization without further training, by utilizing properties of the quantized space to extract aspect-specific summaries. We also make publicly available SPACE, a large-scale evaluation benchmark for opinion summarizers, comprising general and aspect-specific summaries for 50 hotels. Experiments demonstrate the promise of our approach, which is validated by human studies where judges showed clear preference for our method over competitive baselines.