Lune

ACL2023Top-tier venue

Do You Hear The People Sing? Key Point Analysis via Iterative Clustering and Abstractive Summarisation

Hao Li, Viktor Schlegel, Riza Batista-Navarro, Goran Nenadic

Abstract

Argument summarisation is a promising but currently under-explored field. Recent work has aimed to provide textual summaries in the form of concise and salient short texts, i.e., key points (KPs), in a task known as Key Point Analysis (KPA). One of the main challenges in KPA is finding high-quality key point candidates from dozens of arguments even in a small corpus. Furthermore, evaluating key points is crucial in ensuring that the automatically generated summaries are useful. Although automatic methods for evaluating summarisation have considerably advanced over the years, they mainly focus on sentence-level comparison, making it difficult to measure the quality of a summary (a set of KPs) as a whole. Aggravating this problem is the fact that human evaluation is costly and unreproducible. To address the above issues, we propose a two-step abstractive summarisation framework based on neural topic modelling with an iterative clustering procedure, to generate key points which are aligned with how humans identify key points. Our experiments show that our framework advances the state of the art in KPA, with performance improvement of up to 14 (absolute) percentage points, in terms of both ROUGE and our own proposed evaluation metrics 1 . Furthermore, we evaluate the generated summaries using a novel set-based evaluation toolkit. Our quantitative analysis demonstrates the effectiveness of our proposed evaluation metrics in assessing the quality of generated KPs. Human evaluation further demonstrates the advantages of our approach and validates that our proposed evaluation metric is more consistent with human judgment than ROUGE scores. Children express themselves through the clothes they wear and should be able to do this at school School uniform is harming the student's self expression School uniforms are expensive [...] Children should be able to dress as they wish, within reason, at school rather than being restricted from expressing themselves through their clothes. Children should be allowed to express themselves School uniform is unaffordable for many single parents and should be abandoned. School uniforms are an expense that many families can't afford. there are plenty of ways to get very cheap clothing, but discounted uniforms are more difficult to obtain. School uniforms are expensive and puts an undue burden on the parents of the students. School uniforms are expensive for the school and take money from other important programs. School unforms stifle freedom of expression. they can be costly and make circumstances difficult for those on a budget [...] Topic: We should abandon the use of school uniform

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

5 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • ARQUSUMM: Argument-aware Quantitative Summarization of Online Conversations cites BLEURT: Learning Robust Metrics for Text Generation
  • ARQUSUMM: Argument-aware Quantitative Summarization of Online Conversations cites BERTScore: Evaluating Text Generation with BERT
  • ARQUSUMM: Argument-aware Quantitative Summarization of Online Conversations cites PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
  • Argument Summarization and its Evaluation in the Era of Large Language Models cites BLEURT: Learning Robust Metrics for Text Generation
  • Argument Summarization and its Evaluation in the Era of Large Language Models cites BARTScore: Evaluating Generated Text as Text Generation
  • BLEURT: Learning Robust Metrics for Text Generation cites BERTScore: Evaluating Text Generation with BERT
  • BARTScore: Evaluating Generated Text as Text Generation cites BLEURT: Learning Robust Metrics for Text Generation
  • BARTScore: Evaluating Generated Text as Text Generation cites BERTScore: Evaluating Text Generation with BERT
  • BARTScore: Evaluating Generated Text as Text Generation cites PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
  • QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering cites BLEURT: Learning Robust Metrics for Text Generation
  • QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering cites BERTScore: Evaluating Text Generation with BERT
  • QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question Answering cites PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
  • ArgCMV: An Argument Summarization Benchmark for the LLM-era cites Argument Summarization and its Evaluation in the Era of Large Language Models
  • ArgCMV: An Argument Summarization Benchmark for the LLM-era cites BLEURT: Learning Robust Metrics for Text Generation
  • Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement cites Argument Summarization and its Evaluation in the Era of Large Language Models
  • Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement cites BLEURT: Learning Robust Metrics for Text Generation
  • Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware Refinement cites BERTScore: Evaluating Text Generation with BERT
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers5

  1. Arg-LLaDA: Argument Summarization via Large Language Diffusion Models and Sufficiency-Aware RefinementHao Li, Yizheng Sun, Viktor Schlegel, Kailai Yang et al.ACL 2026 · 1 citation
  2. ARQUSUMM: Argument-aware Quantitative Summarization of Online ConversationsAn Quang Tang, Xiuzhen Zhang, Minh Ngoc Dinh, Zhuang LiAAAI 2026
  3. Argument Summarization and its Evaluation in the Era of Large Language ModelsMoritz Altemeyer, Steffen Eger, Johannes Daxenberger, Yanran Chen et al.EMNLP 2025
  4. QQSUM: A Novel Task and Model of Quantitative Query-Focused Summarization for Review-based Product Question AnsweringAn Quang Tang, Xiuzhen Zhang, Minh Ngoc Dinh, Zhuang LiACL 2025
  5. ArgCMV: An Argument Summarization Benchmark for the LLM-eraOmkar Gurjar, Agam Goyal, Eshwar ChandrasekharanEMNLP 2025

Builds on8

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
  3. PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive SummarizationJingqing Zhang, Yao Zhao, Mohammad Saleh, Peter J. LiuICML 2020 · 2,453 citations
  4. BARTScore: Evaluating Generated Text as Text GenerationWeizhe Yuan, Graham Neubig, Pengfei LiuNeurIPS 2021 · 1,143 citations
  5. BLEURT: Learning Robust Metrics for Text GenerationThibault Sellam, Dipanjan Das, Ankur P. ParikhACL 2020 · 40 citations

Related papers

  1. Re-evaluating Evaluation in Text SummarizationManik Bhandari, Pranav Narayan Gour, Atabak Ashfaq, Pengfei Liu et al.EMNLP 2020 · 3 citations
  2. Every Bite Is an Experience: Key Point Analysis of Business ReviewsRoy Bar-Haim, Lilach Eden, Yoav Kantor, Roni Friedman et al.ACL 2021
  3. Prompted Aspect Key Point Analysis for Quantitative Review SummarizationAn Quang Tang, Xiuzhen Zhang, Minh Ngoc Dinh, Erik CambriaACL 2024
  4. Revisiting Automatic Evaluation of Extractive Summarization Task: Can We Do Better than ROUGE?Mousumi Akter, Naman Bansal, Shubhra Kanti Karmaker SantuACL Findings 2022 · 35 citations
  5. SemSUM: Semantic Dependency Guided Neural Abstractive SummarizationHanqi Jin, Tianming Wang, Xiaojun WanAAAI 2020 · 60 citations
Dusk over the sea between two cliffs drawn in fine vertical lines