MARS: Multilingual Aspect-centric Review Summarisation
Not on the map. Why?
Abstract (arXiv)
Summarizing customer feedback to provide actionable insights for products/services at scale is an important problem for businesses across industries. Lately, the review volumes are increasing across regions and languages, therefore the challenge of aggregating and understanding customer sentiment across multiple languages becomes increasingly vital. In this paper, we propose a novel framework involving a two-step paradigm textitExtract-then-Summarise, namely MARS to revolutionise traditions and address the domain agnostic aspect-level multilingual review summarisation. Extensive automatic and human evaluation shows that our approach brings substantial improvements over abstractive baselines and efficiency to real-time systems.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 43 of its 81 references that are in the map. First posted on arXiv 13 Oct 2024.
Builds on
43 of 81 references.
References · 43
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
- 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
- 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
- 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,968
- 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,813
- 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,308
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
- 2020On Faithfulness and Factuality in Abstractive Summarizationcited by 895
- 2016Abstractive Text Summarization Using Sequence-to-Sequence RNNs and Beyondcited by 809
31 more
- 2022A Survey on In-context Learningcited by 717
- 2022Decomposed Prompting: A Modular Approach for Solving Complex Taskscited by 554
- 2019Text Summarization with Pretrained Encoderscited by 553
- 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
- 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
- 2015A Neural Attention Model for Abstractive Sentence Summarizationcited by 394
- 2021XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languagescited by 346
- 2016SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documentscited by 245
- 2019Neural Text Summarization: A Critical Evaluationcited by 189
- 2020Extractive Summarization as Text Matchingcited by 189
- 2018Bottom-Up Abstractive Summarizationcited by 177
- 2018Fast Abstractive Summarization with Reinforce-Selected Sentence Rewritingcited by 158
- 2023Exploring the Limits of ChatGPT for Query or Aspect-based Text Summarizationcited by 122
- 2020MLSUM: The Multilingual Summarization Corpuscited by 121
- 2016Neural Summarization by Extracting Sentences and Wordscited by 114
- 2018Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervisedcited by 75
- 2020What Have We Achieved on Text Summarization?cited by 65
- 2020WikiAsp: A Dataset for Multi-domain Aspect-based Summarizationcited by 56
- 2023SummIt: Iterative Text Summarization via ChatGPTcited by 53
- 2021Aspect-Controllable Opinion Summarizationcited by 47
- 2021ASPECTNEWS: Aspect-Oriented Summarization of News Documentscited by 37
- 2022NEWTS: A Corpus for News Topic-Focused Summarizationcited by 27
- 2022OASum: Large-Scale Open Domain Aspect-based Summarizationcited by 24
- 2019Summary Level Training of Sentence Rewriting for Abstractive Summarizationcited by 23
- 2020Summarizing Text on Any Aspects: A Knowledge-Informed Weakly-Supervised Approachcited by 23
- 2023OpenAsp: A Benchmark for Multi-document Open Aspect-based Summarizationcited by 15
- 2023SWING: Balancing Coverage and Faithfulness for Dialogue Summarizationcited by 10
- 2021Contextualized Rewriting for Text Summarizationcited by 8
- 2020Massive Multi-Document Summarization of Product Reviews with Weak Supervisioncited by 7
- 2015Aspect-based Opinion Summarization with Convolutional Neural Networkscited by 6
- 2024InsightNet: Structured Insight Mining from Customer Feedbackcited by 4
Built on by
Not cited yet.