OpinionDigest: A Simple Framework for Opinion Summarization

04/07/2020

OpinionDigest: A Simple Framework for Opinion Summarization

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

Keywords: Opinion Summarization, Automatic data, Human studies, OpinionDigest

Abstract Paper Similar Papers

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 shows promising customization capabilities.

0

0

0

0

Share

This is an embedded video. Talk and the respective paper are published at ACL 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment

no comments yet

Similar Papers

04/07/2020

Unsupervised Opinion Summarization as Copycat-Review Generation

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Keywords Paper

Unsupervised Summarization, Copycat-Review Generation, Opinion summarization, automatically summaries

0

0

0

0

10:55

16/11/2020

Few-Shot Learning for Opinion Summarization

Arthur Bražinskas, Mirella Lapata, Ivan Titov

Keywords Paper

opinion summarization, automatic text, summary production, summarization mode

0

0

0

0

11:48

16/11/2020

Weakly-Supervised Aspect-Based Sentiment Analysis via Joint Aspect-Sentiment Topic Embedding

Jiaxin Huang, Yu Meng, Fang Guo and
Heng Ji, Jiawei Han

Keywords Paper

extracting aspects, classifying reviews, aspect-based analysis, aspect classification

0

0

0

0

11:23

19/04/2021

Informative and controllable opinion summarization

Reinald Kim Amplayo, Mirella Lapata

Keywords Paper

0

0

0

0

7:39

02/02/2021

Unsupervised Opinion Summarization with Content Planning

Reinald Kim Amplayo, Stefanos Angelidis, Mirella Lapata

Keywords Paper

0

0

0

0

16:03

22/09/2020

Cascading hybrid bandits: Online learning to rank for relevance and diversity

Chang Li, Haoyun Feng, Maarten Rijke

Keywords Paper

recommender system, contextual bandits, Online learning to rank, result diversification

0

0

0

0

2:51

02/02/2021

MetaAugment: Sample-Aware Data Augmentation Policy Learning

Fengwei Zhou, Jiawei Li, Chuanlong Xie and
Fei Chen, Lanqing Hong, Rui Sun, Zhenguo Li

Keywords Paper

0

0

0

0

18:19

22/09/2020

TAFA: Two-headed attention fused autoencoder for context-aware recommendations

Jin Peng Zhou, Zhaoyue Cheng, Felipe Perez, Maksims Volkovs

Keywords Paper

Deep Learning, Context-Aware Recommender Systems, Neural Attention Networks

0

0

0

0

2:06

04/07/2020

Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation

Weixin Liang, James Zou, Zhou Yu

Keywords Paper

Automatic Evaluation, Open evaluation, dialog research, dialog evaluation

0

0

0

0

11:24

14/06/2020

Fine-Grained Generalized Zero-Shot Learning via Dense Attribute-Based Attention

Dat Huynh, Ehsan Elhamifar

Keywords Paper

zero-shot learning, few-shot learning, fine-grained recognition, transfer learning, attention

0

0

0

0

1:01

19/04/2021

Is “hot pizza” positive or negative? Mining target-aware sentiment lexicons

Jie Zhou, Yuanbin Wu, Changzhi Sun, Liang He

Keywords Paper

0

0

0

0

10:19

14/06/2020

Suppressing Uncertainties for Large-Scale Facial Expression Recognition

Kai Wang, Xiaojiang Peng, Jianfei Yang and
Shijian Lu, Yu Qiao

Keywords Paper

emotion recognition, self-cure network, uncertainties

0

0

0

0

1:01

02/02/2021

Aspect-Level Sentiment-Controllable Review Generation with Mutual Learning Framework

Huimin Chen, Yankai Lin, Fanchao Qi and
Jinyi Hu, Peng Li, Jie Zhou, Maosong Sun

Keywords Paper

0

0

0

0

14:57

16/11/2020

Dialogue Response Ranking Training with Large-Scale Human Feedback Data

Xiang Gao, Yizhe Zhang, Michel Galley and
Chris Brockett, Bill Dolan

Keywords Paper

feedback prediction, ranking problem, predicting feedback, open-domain models

0

0

0

0

11:57

08/12/2020

Attentively Embracing Noise for Robust Latent Representation in BERT

Gwenaelle Cunha Sergio, Dennis Singh Moirangthem, Minho Lee

Keywords Paper

0

0

0

0

12:55

04/07/2020

How Can We Accelerate Progress Towards Human-like Linguistic Generalization?

Tal Linzen

Keywords Paper

natural understanding, classification task, Pretraining-Agnostic paradigm, pre-training

0

0

0

0

7:04

04/07/2020

Unsupervised FAQ Retrieval with Question Generation and BERT

Yosi Mass, Boaz Carmeli, Haggai Roitman, David Konopnicki

Keywords Paper

Unsupervised Retrieval, Question Generation, Frequently retrieval, fully method

0

0

0

0

7:16

16/11/2020

Compressive Summarization with Plausibility and Salience Modeling

Shrey Desai, Jiacheng Xu, Greg Durrett

Keywords Paper

compressive systems, compressions, rouge, pre-trained model

0

0

0

0

12:04

14/06/2020

Learning Visual Emotion Representations From Web Data

Zijun Wei, Jianming Zhang, Zhe Lin and
Joon-Young Lee, Niranjan Balasubramanian, Minh Hoai, Dimitris Samaras

Keywords Paper

emotion recognition, visual emotion, emotion feature learning

0

0

0

0

1:02

25/07/2020

Sampler design for implicit feedback data by noisy-label robust learning

Wenhui Yu, Zheng Qin

Keywords Paper

collaborative filtering, bayesian point-wise optimization, noisy-label robust learning, negative sampling, item recommendation

0

0

0

0

12:25

04/07/2020

OpusFilter: A Configurable Parallel Corpus Filtering Toolbox

Mikko Aulamo, Sami Virpioja, Jörg Tiedemann

Keywords Paper

filtering corpora, Finnish-English task, data selection, domain adaptation

0

0

0

0

11:16

25/07/2020

Sampling bias due to near-duplicates in learning to rank

Maik Fröbe, Janek Bevendorff, Jan Heinrich Reimer and
Martin Potthast, Matthias Hagen

Keywords Paper

near-duplicate-detection, selection bias, learning to rank, novelty principle

0

0

0

0

10:59

02/02/2021

Question-Driven Span Labeling Model for Aspect–Opinion Pair Extraction

Lei Gao, Yulong Wang, Tongcun Liu and
Jingyu Wang, Lei Zhang, Jianxin Liao

Keywords Paper

0

0

0

0

15:05

02/02/2021

A Simple and Effective Self-Supervised Contrastive Learning Framework for Aspect Detection

Tian Shi, Liuqing Li, Ping Wang, Chandan K. Reddy

Keywords Paper

0

0

0

0

19:21

04/07/2020

Unsupervised Opinion Summarization with Noising and Denoising

Reinald Kim Amplayo, Mirella Lapata

Keywords Paper

Unsupervised Summarization, supervised models, abstractive summarization, Noising

0

0

0

0

12:16

22/09/2020

A ranking optimization approach to latent linear critiquing for conversational recommender systems

Hanze Li, Scott Sanner, Kai Luo, Ga Wu

Keywords Paper

Critiquing, Conversational Recommendation

0

0

0

0

2:54

06/12/2020

Learning to summarize with human feedback

Nisan Stiennon, Long Ouyang, Jeffrey Wu and
Daniel Ziegler, Ryan Lowe, Chelsea Voss, Alec Radford, Dario Amodei, Paul Christiano

Keywords Paper

0

0

0

0

3:17

04/07/2020

uBLEU: Uncertainty-Aware Automatic Evaluation Method for Open-Domain Dialogue Systems

Tsuta Yuma, Naoki Yoshinaga, Masashi Toyoda

Keywords Paper

Open-Domain Systems, uBLEU, Uncertainty-Aware Method, ΔBLEU

0

0

0

0

11:07

14/06/2020

Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization

Lourenço V. Pato, Renato Negrinho, Pedro M. Q. Aguiar

Keywords Paper

object detection, context, rescoring, average precision, non-maximum suppression

0

0

0

0

1:00

26/04/2020

I Am Going MAD: Maximum Discrepancy Competition for Comparing Classifiers Adaptively

Haotao Wang, Tianlong Chen, Zhangyang Wang, Kede Ma

Keywords Paper

model comparison

0

0

0

0

4:53

23/08/2020

AutoFIS: Automatic feature interaction selection in factorization models for click-through rate prediction

Bin Liu, Chenxu Zhu, Guilin Li and
Weinan Zhang, Jincai Lai, Ruiming Tang, Xiuqiang He, Zhenguo Li, Yong Yu

Keywords Paper

feature selection, neural architecture search, recommendation, factorization machine

0

0

0

0

19:23

04/07/2020

Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning

Hongliang Fei, Ping Li

Keywords Paper

Cross-Lingual Classification, sentiment classification, unsupervised system, classification

0

0

0

0

12:23

08/12/2020

ContraCAT: Contrastive Coreference Analytical Templates for Machine Translation

Dario Stojanovski, Benno Krojer, Denis Peskov, Alexander Fraser

Keywords Paper

0

0

0

0

14:09

03/05/2021

Task-Agnostic Morphology Evolution

Donald Hejna III, Pieter Abbeel, Lerrel Pinto

Keywords Paper

evolution, morphology, empowerment, unsupervised, information theory

0

0

0

0

3:59

02/02/2021

Merging Statistical Feature via Adaptive Gate for Improved Text Classification

Xianming Li, Zongxi Li, Haoran Xie, Qing Li

Keywords Paper

0

0

0

0

14:56

25/07/2020

A unified dual-view model for review summarization and sentiment classification with inconsistency loss

Hou Pong Chan, Wang Chen, Irwin King

Keywords Paper

multi-task learning, review summarization, text summarization, sentiment classification

0

0

0

0

14:59

04/07/2020

SKEP: Sentiment Knowledge Enhanced Pre-training for Sentiment Analysis

Hao Tian, Can Gao, Xinyan Xiao and
Hao Liu, Bolei He, Hua Wu, Haifeng Wang, Feng Wu

Keywords Paper

Sentiment Pre-training, Sentiment Analysis, pre-training, sentiment tasks

0

0

0

0

11:39

16/11/2020

HABERTOR: An Efficient and Effective Deep Hatespeech Detector

Thanh Tran, Yifan Hu, Changwei Hu and
Kevin Yen, Fei Tan, Kyumin Lee, Se Rim Park

Keywords Paper

downstream task, hatespeech classification, habertor model, bert model

0

0

0

0

11:46

04/07/2020

SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization

Yang Gao, Wei Zhao, Steffen Eger

Keywords Paper

Multi-Document Summarization, SUPERT, contextualized embeddings, soft techniques

0

0

0

0

7:46

04/07/2020

Relabel the Noise: Joint Extraction of Entities and Relations via Cooperative Multiagents

Daoyuan Chen, Yaliang Li, Kai Lei, Ying Shen

Keywords Paper

entity extraction, re-labeling instances, extraction tasks, re-labeling instance

0

0

0

0

11:24