OpinionDigest: A Simple Framework for Opinion Summarization

Suhara, Yoshihiko; Wang, Xiaolan; Angelidis, Stefanos; Tan, Wang-Chiew

doi:10.18653/v1/2020.acl-main.513

Cited by 54 publications

(38 citation statements)

References 16 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More recently, (Tan et al, 2017) suggested a novel generative topic aspect sentiment model, while ) suggested a novel system able to extract both general and aspect-specific summaries. As for abstractive summarization, recent advances on pre-training neural networks were explored in the context of product reviews in unsupervised and few-shot learning schemes which led to promising results (Chu and Liu, 2019;Brazinskas et al, 2020b,a;Suhara et al, 2020;.…”

Section: Related Workmentioning

confidence: 99%

PASS: Perturb-and-Select Summarizer for Product Reviews

Oved¹,

Levy²

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

The product reviews summarization task aims to automatically produce a short summary for a set of reviews of a given product. Such summaries are expected to aggregate a range of different opinions in a concise, coherent and informative manner. This challenging task gives rise to two shortcomings in existing work. First, summarizers tend to favor generic content that appears in reviews for many different products, resulting in template-like, less informative summaries. Second, as reviewers often disagree on the pros and cons of a given product, summarizers sometimes yield inconsistent, self-contradicting summaries. We propose the PASS system (Perturb-and-Select Summarizer) that employs a large pre-trained Transformer-based model (T5 in our case), which follows a few-shot fine-tuning scheme.A key component of the PASS system relies on applying systematic perturbations to the model's input during inference, which allows it to generate multiple different summaries per product. We develop a method for ranking these summaries according to desired criteria, coherence in our case, enabling our system to almost entirely avoid the problem of selfcontradiction. We compare our system against strong baselines on publicly available datasets, and show that it produces summaries which are more informative, diverse and coherent. 1 * Completed during an internship at Amazon.

show abstract

Section: Related Workmentioning

confidence: 99%

PASS: Perturb-and-Select Summarizer for Product Reviews

Oved¹,

Levy²

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…Recently, several abstractive neural summarization methods have shown promising results. These models require no summaries for training (Chu and Liu, 2019;Bražinskas et al, 2020b;Suhara et al, 2020), or only a handful of them (Bražinskas et al, 2020a). As discussed in the previous section, textual summaries provide more detail than aspect-based sentiment summaries, but lack a quantitative dimension.…”

Section: Related Workmentioning

confidence: 99%

Every Bite Is an Experience: Key Point Analysis of Business Reviews

Bar-Haim¹,

Eden²,

Kantor³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Previous work on review summarization focused on measuring the sentiment toward the main aspects of the reviewed product or business, or on creating a textual summary. These approaches provide only a partial view of the data: aspect-based sentiment summaries lack sufficient explanation or justification for the aspect rating, while textual summaries do not quantify the significance of each element, and are not well-suited for representing conflicting views. Recently, Key Point Analysis (KPA) has been proposed as a summarization framework that provides both textual and quantitative summary of the main points in the data. We adapt KPA to review data by introducing Collective Key Point Mining for better key point extraction; integrating sentiment analysis into KPA; identifying good key point candidates for review summaries; and leveraging the massive amount of available reviews and their metadata. We show empirically that these novel extensions of KPA substantially improve its performance. We demonstrate that promising results can be achieved without any domain-specific annotation, while human supervision can lead to further improvement.

show abstract

“…A concurrent model DENOISESUM (Amplayo and Lapata, 2020) uses a syntactically generated dataset of source reviews to train a generator to denoise and distill common information. Another parallel work, OPINIONDIGEST (Suhara et al, 2020), considers controllable opinion aggregation and is a pipeline framework for abstractive summary generation. Our conditioning on text properties approach is similar to Ficler and Goldberg ( 2017), yet we rely on automatically derived properties that associate a target to source, and learn a separate module to generate their combinations.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Learning for Opinion Summarization

Arthur

Lapata

Titov

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents, such as user reviews of a product. The task is practically important and has attracted a lot of attention. However, due to the high cost of summary production, datasets large enough for training supervised models are lacking. Instead, the task has been traditionally approached with extractive methods that learn to select text fragments in an unsupervised or weakly-supervised way. Recently, it has been shown that abstractive summaries, potentially more fluent and better at reflecting conflicting information, can also be produced in an unsupervised fashion. However, these models, not being exposed to actual summaries, fail to capture their essential properties. In this work, we show that even a handful of summaries is sufficient to bootstrap generation of the summary text with all expected properties, such as writing style, informativeness, fluency, and sentiment preservation. We start by training a conditional Transformer language model to generate a new product review given other available reviews of the product. The model is also conditioned on review properties that are directly related to summaries; the properties are derived from reviews with no manual effort. In the second stage, we fine-tune a plug-in module that learns to predict property values on a handful of summaries. This lets us switch the generator to the summarization mode. We show on Amazon and Yelp datasets that our approach substantially outperforms previous extractive and abstractive methods in automatic and human evaluation.

show abstract

OpinionDigest: A Simple Framework for Opinion Summarization

Cited by 54 publications

References 16 publications

PASS: Perturb-and-Select Summarizer for Product Reviews

PASS: Perturb-and-Select Summarizer for Product Reviews

Every Bite Is an Experience: Key Point Analysis of Business Reviews

Few-Shot Learning for Opinion Summarization

Contact Info

Product

Resources

About