OpinionDigest: A Simple Framework for Opinion Summarization
Yoshihiko Suhara, Xiaolan Wang, Stefanos Angelidis, Wang-Chiew Tan

TL;DR
OpinionDigest is a novel framework for opinion summarization that uses aspect-based sentiment analysis and a Transformer model to generate customizable, abstractive summaries without relying on gold-standard training data.
Contribution
It introduces a simple, training-free approach combining opinion extraction and a Transformer for abstractive summarization, enabling customization and outperforming baselines.
Findings
Outperforms competitive baselines on Yelp data
Produces informative and customizable summaries
Verifies effectiveness through human studies
Abstract
We present OpinionDigest, an abstractive opinion summarization framework, which does not rely on gold-standard summaries for training. The framework uses an Aspect-based Sentiment Analysis model to extract opinion phrases from reviews, and trains a Transformer model to reconstruct the original reviews from these extractions. At summarization time, we merge extractions from multiple reviews and select the most popular ones. The selected opinions are used as input to the trained Transformer model, which verbalizes them into an opinion summary. OpinionDigest can also generate customized summaries, tailored to specific user needs, by filtering the selected opinions according to their aspect and/or sentiment. Automatic evaluation on Yelp data shows that our framework outperforms competitive baselines. Human studies on two corpora verify that OpinionDigest produces informative summaries and…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Sentiment Analysis and Opinion Mining · Advanced Text Analysis Techniques
MethodsLinear Layer · Absolute Position Encodings · Position-Wise Feed-Forward Layer · Residual Connection · Byte Pair Encoding · Dense Connections · Label Smoothing · *Communicated@Fast*How Do I Communicate to Expedia? · Adam · Softmax
