OpinionDigest: A Simple Framework for Opinion Summarization

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.

[1]  Dragomir R. Radev,et al.  LexRank: Graph-based Lexical Centrality as Salience in Text Summarization , 2004, J. Artif. Intell. Res..

[2]  Yangqiu Song,et al.  Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision , 2019, ACL.

[3]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[4]  Mirella Lapata,et al.  Informative and Controllable Opinion Summarization , 2019, EACL.

[5]  Bing Liu,et al.  DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction , 2019, ACL.

[6]  Xiaokui Xiao,et al.  Coupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms , 2017, AAAI.

[7]  Yuliang Li,et al.  Snippext: Semi-supervised Opinion Mining with Augmented Data , 2020, WWW.

[8]  Ichiro Sakata,et al.  Unsupervised Neural Single-Document Summarization of Reviews via Learning Latent Discourse Structure and its Ranking , 2019, ACL.

[9]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[10]  Eric Chu,et al.  MeanSum: A Neural Model for Unsupervised Multi-Document Abstractive Summarization , 2018, ICML.

[11]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[12]  Mirella Lapata,et al.  Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised , 2018, EMNLP.

[13]  Jinfeng Li,et al.  Subjective Databases , 2019, Proc. VLDB Endow..

[14]  Jinfeng Li,et al.  ExtremeReader: An interactive explorer for customizable and explainable review summarization , 2020, WWW.

[15]  Bing Liu,et al.  Mining Opinion Features in Customer Reviews , 2004, AAAI.

[16]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[17]  Jordan J. Louviere,et al.  Best-Worst Scaling: Theory, Methods and Applications , 2015 .

[18]  Mirella Lapata,et al.  Neural Summarization by Extracting Sentences and Words , 2016, ACL.

[19]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[20]  Ivan Titov,et al.  Unsupervised Opinion Summarization as Copycat-Review Generation , 2020, ACL.

[21]  Mirella Lapata,et al.  Hierarchical Transformers for Multi-Document Summarization , 2019, ACL.

[22]  Mirella Lapata,et al.  Unsupervised Multi-Document Opinion Summarization as Copycat-Review Generation , 2019, ArXiv.

[23]  Saif Mohammad,et al.  Capturing Reliable Fine-Grained Sentiment Associations by Crowdsourcing and Best–Worst Scaling , 2016, NAACL.