• Corpus ID: 239016115

Fine-Grained Opinion Summarization with Minimal Supervision

@article{Ge2021FineGrainedOS,
  title={Fine-Grained Opinion Summarization with Minimal Supervision},
  author={Suyu Ge and Jiaxin Huang and Yu Meng and Sharon Wang and Jiawei Han},
  journal={ArXiv},
  year={2021},
  volume={abs/2110.08845}
}
Opinion summarization aims to profile a target by extracting opinions from multiple documents. Most existing work approaches the task in a semi-supervised manner due to the difficulty of obtaining high-quality annotation from thousands of documents. Among them, some uses aspect and sentiment analysis as a proxy for identifying opinions. In this work, we propose a new framework, FineSum, which advances this frontier in three aspects: (1) minimal supervision, where only aspect names and a few… 
Unsupervised Summarization with Customized Granularities
TLDR
This paper proposes the first unsupervised multi-granularity summarization framework, GranuSum, which takes events as the basic semantic units of the source documents and proposes to rank these events by their salience, and develops a model to summarize input documents with given events as anchors and hints.

References

SHOWING 1-10 OF 23 REFERENCES
Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised
TLDR
An opinion summarization dataset is introduced that includes a training set of product reviews from six diverse domains and human-annotated development and test sets with gold standard aspect annotations, salience labels, and opinion summaries.
OpinionDigest: A Simple Framework for Opinion Summarization
TLDR
OpinionDigest, an abstractive opinion summarization framework, which 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.
Inducing Document Structure for Aspect-based Summarization
TLDR
It is shown that the benefit of the learnt document structure can leverage the structure to produce both abstractive and extractive aspect-based summaries, and that structure is particularly advantageous for summarizing long documents.
Opinion Extraction, Summarization and Tracking in News and Blog Corpora
TLDR
Both news and web blog articles are investigated and algorithms for opinion extraction at word, sentence and document level are proposed, and the issue of relevant sentence selection is discussed, and then topical and opinionated information are summarized.
Informative and Controllable Opinion Summarization
TLDR
This paper proposes a summarization framework that eliminates the need to rely only on pre-selected content and waste possibly useful information, especially when customizing summaries, and enables the use of all input reviews by first condensing them into multiple dense vectors which serve as input to an abstractive model.
W2VLDA: Almost unsupervised system for Aspect Based Sentiment Analysis
MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization
TLDR
This work considers the setting where there are only documents with no summaries provided, and proposes an end-to-end, neural model architecture to perform unsupervised abstractive summarization, and shows that the generated summaries are highly abstractive, fluent, relevant, and representative of the average sentiment of the input reviews.
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects
TLDR
This work proposes an ‘extractive’ approach to identify review segments which justify users’ intentions and designs two personalized generation models which can generate diverse justifications based on templates extracted from justification histories.
Summarizing Contrastive Viewpoints in Opinionated Text
TLDR
Experimental results show that the proposed approach can generate informative summaries of viewpoints in opinionatedText, with significant performance gains over bag-of-words feature sets.
Extractive Opinion Summarization in Quantized Transformer Spaces
TLDR
The Quantized Transformer is inspired by Vector- Quantized Variational Autoencoders and 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.
...
...