--- title: "Extractive Opinion Summarization in Quantized Transformer" description: "The authors propose the Quantized Transformer (QT), an unsupervised extractive model adapted from… 3 references, cited by 68 papers here." authors: ["Stefanos Angelidis", "Reinald Kim Amplayo", "Yoshihiko Suhara", "Xiaolan Wang", "Mirella Lapata"] year: 2021 venue: "Transactions of the Association for Computational Linguistics" source: "https://aclanthology.org/2021.tacl-1.17/" doi: "10.1162/tacl_a_00366" licence: "CC BY 4.0 (ACL Anthology)" licence_url: "https://creativecommons.org/licenses/by/4.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/angelidis-2021-extractive-opinion-summarization-quantized-transformer/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/angelidis-2021-extractive-opinion-summarization-quantized-transformer/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/3/) / Extractive Opinion Summarization in Quantized Transformer Spaces # Extractive Opinion Summarization in Quantized Transformer Spaces **Authors:** [Stefanos Angelidis](https://md.research.elamur.ai/free/en/authors/stefanos-angelidis/), [Reinald Kim Amplayo](https://md.research.elamur.ai/free/en/authors/reinald-kim-amplayo/), Yoshihiko Suhara, Xiaolan Wang and [Mirella Lapata](https://md.research.elamur.ai/free/en/authors/mirella-lapata/) · **Year:** 2021 · **Venue:** [Transactions of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/tacl/) ([Transactions of the Association for Computational Linguistics (TACL) 2021](https://md.research.elamur.ai/free/en/venues/tacl/2021/)) · **Publisher:** [The MIT Press](https://md.research.elamur.ai/free/en/publishers/the-mit-press/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/2021.tacl-1.17/) · [PDF](https://aclanthology.org/2021.tacl-1.17.pdf) · [DOI 10.1162/tacl\_a\_00366](https://doi.org/10.1162/tacl_a_00366) · [OpenAlex](https://openalex.org/W3113219314) **Citations:** 83 citations (OpenAlex, 2026-10-14) · [68](https://md.research.elamur.ai/free/en/papers/angelidis-2021-extractive-opinion-summarization-quantized-transformer/cited-by/) in our library, of the 141,840 papers whose bibliographies we read ## Summary Opinion summarization means condensing what many reviewers say about one entity. Training references barely exist, inputs can reach thousands of reviews, and users may want either an overview or a focus on one aspect. Abstractive systems that learn by reconstructing reviews tend to hallucinate and slip into first-person phrasing, and they were tested on ten or fewer reviews. The authors propose the Quantized Transformer (QT), an unsupervised extractive model adapted from VQ-VAE. A Transformer encoder splits each sentence into several head vectors, which are mapped onto a shared codebook of discrete latent codes. Training uses sentence reconstruction with Soft EM. At inference, the codes act as clusters, and sentences tied to the most populated codes form the summary. Aspect summaries need no retraining: the system automatically picks the head with the lowest aspect entropy and queries it with a few aspect keywords. The authors also release SPACE, a TripAdvisor hotel benchmark. QT beats strong baselines on SPACE and two other benchmarks, and human judges preferred its output. ## Key points - SPACE contains 1,050 human-written summaries for 50 hotels, both general and aspect-specific. Each summary draws on 100 reviews, about ten times more input than earlier benchmarks. - Aspect summaries cover six aspects (building, cleanliness, food, location, rooms, service). QT leads the baselines on all of them except building. - In a human study, 58.7% of QT's aspect summaries stayed exclusively on the requested aspect, and only 8.7% ignored it. For LexRank_ASP, 23.8% of summaries missed the aspect, and MeanSum and Copycat did worse still. - Trained on just 5% of the data, QT roughly matches Copycat trained on the full corpus (ROUGE-1 on SPACE). - An eight-head QT learned 1024 latent codes. A t-SNE plot shows one head forming an aspect-separating sub-space without any aspect supervision. Code is at github.com/stangelid/qt. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* ## Institutions - [University of Edinburgh](https://md.research.elamur.ai/free/en/universities/university-of-edinburgh/) — University, Edinburgh, United Kingdom · 255 works · 68,771 citations 📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 8,888 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 9,296 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 9,206 works 🧭 Topics (1): [📝 Summarization](https://md.research.elamur.ai/free/en/topics/summarization/) · 159 works ## Cite Cite as: Stefanos Angelidis, Reinald Kim Amplayo, Yoshihiko Suhara, Xiaolan Wang and Mirella Lapata. 2021. Extractive Opinion Summarization in Quantized Transformer Spaces. Transactions of the Association for Computational Linguistics. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @article{angelidis2021extractive, title = {{Extractive Opinion Summarization in Quantized Transformer Spaces}}, author = {Stefanos Angelidis, Reinald Kim Amplayo, Yoshihiko Suhara, Xiaolan Wang and Mirella Lapata}, journal = {Transactions of the Association for Computational Linguistics}, year = {2021}, doi = {10.1162/tacl\_a\_00366}, url = {https://doi.org/10.1162/tacl_a_00366} } ``` - [← previous Trafilatura: A Web Scraping Library and Command-Line Tool for Text Discovery and Extraction](https://md.research.elamur.ai/free/en/papers/barbaresi-2021-trafilatura-web-scraping-library-command/) - [next → Investigating Pretrained Language Models for Graph-to-Text Generation](https://md.research.elamur.ai/free/en/papers/ribeiro-2021-investigating-pretrained-language-models-graph/) - [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/3/) ## References 3 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Reinald Kim Amplayo and Mirella Lapata. 2019. Informative and controllable opinion summarization. arXiv preprint arXiv:1909.02322v1. [find](https://scholar.google.com/scholar?q=Reinald+Kim+Amplayo+and+Mirella+Lapata%2E+2019%2E+Informative+and+controllable+opinion+summarization%2E+arXiv+preprint+arXiv%3A1909%2E02322v1%2E) 2. System Output Finally, we show gold-standard and system-generated general summaries in Table 8, as well as QT aspect summaries in Table 9. [find](https://scholar.google.com/scholar?q=System+Output+Finally%2C+we+show+gold%2Dstandard+and+system%2Dgenerated+general+summaries+in+Table+8%2C+as+well+as+QT+aspect+summaries+in+Table+9%2E) 3. Reinald Kim Amplayo and Mirella Lapata. 2020. Unsupervised opinion summarization with noising and denoising. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 1934–1945. Association for Computational Linguistics. DOI: https://doi.org/10.18653/v1 /2020.… [find](https://scholar.google.com/scholar?q=Reinald+Kim+Amplayo+and+Mirella+Lapata%2E+2020%2E+Unsupervised+opinion+summarization+with+noising+and+denoising%2E+In+Proceedings+of+the+58th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C) *Updated 24 October 2026*