CLDec 8, 2020

Extractive Opinion Summarization in Quantized Transformer Spaces

arXiv:2012.04443v10.00669 citations
AI Analysis65

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes