Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised
Open accessThe DOI matches its Crossref record; 45 of the 45 references it cites were found in a registry or an index.
Abstract
We present a neural framework for opinion summarization from online product reviews which is knowledge-lean and only requires light supervision (e.g., in the form of product domain labels and user-provided ratings).Our method combines two weakly supervised components to identify salient opinions and form extractive summaries from multiple reviews: an aspect extractor trained under a multi-task objective, and a sentiment predictor based on multiple instance learning.We introduce an opinion summarization dataset 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.Automatic evaluation shows significant improvements over baselines, and a largescale study indicates that our opinion summaries are preferred by human judges according to multiple criteria.1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We used the Adam optimizer (Kingma and Ba, 2014) with learning rate 10 − 4 and mini-batch size 50, and trained for 10 epochs.”
MethodDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 1×
“We initialized MATE using 200-dimensional word embed-dings trained on each product domain using skip-gram (Mikolov et al., 2013) with default parameters.”
MethodConvolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 2×
“Sentiment Prediction Fully-supervised approaches based on neural networks have achieved impressive results on fine-grained sentiment classification (Kim, 2014; Socher et al., 2013).”
MethodMining and summarizing customer reviews
Hu, M., & Liu, B. (2004) · Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1014052.1014073 · Cited by 7,793 · cited 6×
“Various lexicon and rule-based methods (Hu and Liu, 2004; Ku et al., 2006; Blair-Goldensohn et al., 2008) have been adopted for sentiment prediction together with a few learning approaches (Lu et al.”
BackgroundMethodInfluentialRecursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878 · cited 1×
“Sentiment Prediction Fully-supervised approaches based on neural networks have achieved impressive results on fine-grained sentiment classification (Kim, 2014; Socher et al., 2013).”
MethodRhetorical Structure Theory: Toward a functional theory of text organization
MANN, W. C., & THOMPSON, S. A. (1988) · Text - Interdisciplinary Journal for the Study of Discourse · doi:10.1515/text.1.1988.8.3.243 · Cited by 3,853 · cited 1×
“A segment can be a sentence, a phrase, or in our case an Elementary Discourse Unit (EDU; Mann and Thompson 1988) obtained from a Rhetorical Structure Theory (RST) parser (Feng and Hirst, 2012).”
MethodSentiment Analysis and Opinion Mining
Zhang, L., & Liu, B. (2017) · Encyclopedia of Machine Learning and Data Mining · doi:10.1007/978-1-4899-7687-1_907 · Cited by 3,260
Image-Based Recommendations on Styles and Substitutes
McAuley, J., Targett, C., Shi, Q., & van den Hengel, A. (2015) · Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/2766462.2767755 · Cited by 2,280 · cited 1×
“The six training collections were created by down-sampling from the Amazon Product Dataset 3 introduced in McAuley et al. (2015) and contain reviews and their respective ratings.”
MethodStatistical Significance Tests for Machine Translation Evaluation.
Koehn, P. (2004) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · Cited by 2,205
Extracting product features and opinions from reviews
Popescu, A.-M., & Etzioni, O. (2005) · Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05 · doi:10.3115/1220575.1220618 · Cited by 1,698 · cited 2×
“…following mostly extractive methods (but see Ganesan et al. 2010 for an abstractive approach), and various formats ranging from lists of words (Popescu and Etzioni, 2005), to phrases (Lu et al., 2009), and sentences (Mei et al., 2007; Blair-Goldensohn et al., 2008; Lerman et al., 2009; Wang…”
Method
Cited by
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects
Ni, J., Li, J., & McAuley, J. (2019) · Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP) · doi:10.18653/v1/d19-1018 · Cited by 1,200
Issues and Challenges of Aspect-based Sentiment Analysis: A Comprehensive Survey
Nazir, A., Rao, Y., Wu, L., & Sun, L. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2020.2970399 · Cited by 370
An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis
He, R., Lee, W. S., Ng, H. T., & Dahlmeier, D. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1048 · Cited by 277
Can We Automate Scientific Reviewing?
Yuan, W., Liu, P., & Neubig, G. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12862 · Cited by 96
Extractive Opinion Summarization in Quantized Transformer Spaces
Angelidis, S., Amplayo, R. K., Suhara, Y., Wang, X., & Lapata, M. (2021) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00366 · Cited by 85
“More recently, Angelidis and Lapata (2018) extract salient opinions according to their polarity intensity and aspect specificity, in a weakly supervised setting.”
BackgroundMethodInfluentialSelf-citationSelf-Supervised and Controlled Multi-Document Opinion Summarization
Elsahar, H., Coavoux, M., Gallé, M., & Rozen, J. (2020) · arXiv · doi:10.48550/arxiv.2004.14754 · Cited by 40
“In the absence of such meta-data information several approaches have relied instead creating seed lexicons using unsupervised or weakly supervised aspect extractors (He et al., 2017; Angelidis & Lapata, 2018) Hierarchical encoding.”
MethodScientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation
Zeng, Q., Sidhu, M., Blume, A., Chan, H. P., Wang, L., & Ji, H. (2025) · Lecture Notes in Computer Science · doi:10.1007/978-981-97-9536-9_2 · Cited by 2
Scientific Opinion Summarization: Paper Meta-review Generation Dataset, Methods, and Evaluation
Zeng, Q., Sidhu, M., Blume, A., Chan, H. P., Wang, L., & Ji, H. (2023) · arXiv · doi:10.48550/arxiv.2305.14647 · Cited by 2
Metadata
- Authors
- Angelidis, S., & Lapata, M.
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 3675-3686
- OpenAlex
- W2888507208
- Cited by
- 178
- References
- 45
- FWCI
- 9.67
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.