Extractive Opinion Summarization in Quantized Transformer Spaces
- URL: http://arxiv.org/abs/2012.04443v1
- Date: Tue, 8 Dec 2020 14:23:46 GMT
- Title: Extractive Opinion Summarization in Quantized Transformer Spaces
- Authors: Stefanos Angelidis, Reinald Kim Amplayo, Yoshihiko Suhara, Xiaolan
Wang, Mirella Lapata
- Abstract summary: 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.
- Score: 52.95867345952894
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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.
Related papers
- Rationale-based Opinion Summarization [23.39553692130953]
We propose a new paradigm for summarizing reviews, rationale-based opinion summarization.
We define four desirable properties: relatedness, specificity, popularity, and diversity.
To extract good rationales, we define four desirable properties: relatedness, specificity, popularity, and diversity.
arXiv Detail & Related papers (2024-03-30T02:22:57Z) - Incremental Extractive Opinion Summarization Using Cover Trees [81.59625423421355]
In online marketplaces user reviews accumulate over time, and opinion summaries need to be updated periodically.
In this work, we study the task of extractive opinion summarization in an incremental setting.
We present an efficient algorithm for accurately computing the CentroidRank summaries in an incremental setting.
arXiv Detail & Related papers (2024-01-16T02:00:17Z) - Large-Scale and Multi-Perspective Opinion Summarization with Diverse
Review Subsets [23.515892409202344]
SUBSUMM is a supervised summarization framework for large-scale multi-perspective opinion summarization.
It generates pros, cons, and verdict summaries from hundreds of input reviews.
arXiv Detail & Related papers (2023-10-20T08:08:13Z) - Attributable and Scalable Opinion Summarization [79.87892048285819]
We generate abstractive summaries by decoding frequent encodings, and extractive summaries by selecting the sentences assigned to the same frequent encodings.
Our method is attributable, because the model identifies sentences used to generate the summary as part of the summarization process.
It scales easily to many hundreds of input reviews, because aggregation is performed in the latent space rather than over long sequences of tokens.
arXiv Detail & Related papers (2023-05-19T11:30:37Z) - Learning Opinion Summarizers by Selecting Informative Reviews [81.47506952645564]
We collect a large dataset of summaries paired with user reviews for over 31,000 products, enabling supervised training.
The content of many reviews is not reflected in the human-written summaries, and, thus, the summarizer trained on random review subsets hallucinates.
We formulate the task as jointly learning to select informative subsets of reviews and summarizing the opinions expressed in these subsets.
arXiv Detail & Related papers (2021-09-09T15:01:43Z) - Multi-Perspective Abstractive Answer Summarization [76.10437565615138]
Community Question Answering forums contain a rich resource of answers to a wide range of questions.
The goal of multi-perspective answer summarization is to produce a summary that includes all perspectives of the answer.
This work introduces a novel dataset creation method to automatically create multi-perspective, bullet-point abstractive summaries.
arXiv Detail & Related papers (2021-04-17T13:15:29Z) - CTRLsum: Towards Generic Controllable Text Summarization [54.69190421411766]
We presentsum, a novel framework for controllable summarization.
Our approach enables users to control multiple aspects of generated summaries by interacting with the summarization system.
Using a single unified model,sum is able to achieve a broad scope of summary manipulation at inference time.
arXiv Detail & Related papers (2020-12-08T08:54:36Z) - Read what you need: Controllable Aspect-based Opinion Summarization of
Tourist Reviews [23.7107052882747]
We argue the need and propose a solution for generating personalized aspect-based opinion summaries from online tourist reviews.
We let our readers decide and control several attributes of the summary such as the length and specific aspects of interest.
Specifically, we take an unsupervised approach to extract coherent aspects from tourist reviews posted on TripAdvisor.
arXiv Detail & Related papers (2020-06-08T15:03:38Z) - OpinionDigest: A Simple Framework for Opinion Summarization [22.596995566588422]
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.
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.
arXiv Detail & Related papers (2020-05-05T01:22:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.