Lune

ACL Findings2021

Contrastive Aligned Joint Learning for Multilingual Summarization

Danqing Wang, Jiaze Chen, Hao Zhou, Xipeng Qiu, Lei Li

Abstract

Multilingual text summarization requires the ability to understand documents in multiple languages and generate summaries in the corresponding language, which poses more challenges on current summarization systems. However, this problem has been rarely studied due to the lack of large-scale supervised summarization data in multiple languages. In this paper, we first provide a large-scale multilingual summarization corpus MLGSum consisting of 1.1 million articles and summaries in 12 different languages. Based on it, we develop a unified summarization model to understand the document and generate summaries in different languages. We use the contrastive learning strategy to train our multilingual summarization system (CALMS), which consists of two training objectives, contrastive sentence ranking (CSR) and sentence aligned substitution (SAS). The two training objectives are designed to share salient information extractive ability and align sentencelevel representation across different languages. Experimental results indicate that CALMS achieves significant improvement over monolingual models in all languages. We further transfer CALMS to other languages and find that it will also benefit similar languages. Our code and dataset are available at https://github.com/brxx122/CALMS.

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.

7 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

  • Towards Unifying Multi-Lingual and Cross-Lingual Summarization cites Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization
  • Towards Unifying Multi-Lingual and Cross-Lingual Summarization cites A Variational Hierarchical Model for Neural Cross-Lingual Summarization
  • Towards Unifying Multi-Lingual and Cross-Lingual Summarization cites PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
  • Extractive Summarization as Text Matching cites Heterogeneous Graph Neural Networks for Extractive Document Summarization
  • Heterogeneous Graph Neural Networks for Extractive Document Summarization cites Extractive Summarization as Text Matching
  • Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization cites A Variational Hierarchical Model for Neural Cross-Lingual Summarization
  • Summary-Oriented Vision Modeling for Multimodal Abstractive Summarization cites PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers7

  1. A Variational Hierarchical Model for Neural Cross-Lingual SummarizationYunlong Liang, Fandong Meng, Chulun Zhou, Jinan Xu et al.ACL 2022 · 36 citations
  2. Towards Unifying Multi-Lingual and Cross-Lingual SummarizationJiaan Wang, Fandong Meng, Duo Zheng, Yunlong Liang et al.ACL 2023 · 24 citations
  3. CitationSum: Citation-aware Graph Contrastive Learning for Scientific Paper SummarizationZheheng Luo, Qianqian Xie, Sophia AnaniadouWWW 2023 · 19 citations
  4. Summary-Oriented Vision Modeling for Multimodal Abstractive SummarizationYunlong Liang, Fandong Meng, Jinan Xu, Jiaan Wang et al.ACL 2023 · 17 citations
  5. R2D2: Robust Data-to-Text with Replacement DetectionLinyong Nan, Lorenzo Jaime Yu Flores, Yilun Zhao, Yixin Liu et al.EMNLP 2022 · 10 citations

Builds on8

  1. PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive SummarizationJingqing Zhang, Yao Zhao, Mohammad Saleh, Peter J. LiuICML 2020 · 2,453 citations
  2. Extractive Summarization as Text MatchingMing Zhong, Pengfei Liu, Yiran Chen, Danqing Wang et al.ACL 2020 · 410 citations
  3. Heterogeneous Graph Neural Networks for Extractive Document SummarizationDanqing Wang, Pengfei Liu, Yining Zheng, Xipeng Qiu et al.ACL 2020 · 275 citations
  4. Pre-training via ParaphrasingMike Lewis, Marjan Ghazvininejad, Gargi Ghosh, Armen Aghajanyan et al.NeurIPS 2020 · 165 citations
  5. Pre-training Multilingual Neural Machine Translation by Leveraging Alignment InformationZehui Lin, Xiao Pan, Mingxuan Wang, Xipeng Qiu et al.EMNLP 2020 · 82 citations

Related papers

  1. MLSUM: The Multilingual Summarization CorpusThomas Scialom, Paul-Alexis Dray, Sylvain Lamprier, Benjamin Piwowarski et al.EMNLP 2020 · 4 citations
  2. Jointly Learning to Align and Summarize for Neural Cross-Lingual SummarizationYue Cao, Hui Liu, Xiaojun WanACL 2020 · 52 citations
  3. CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1, 500+ Language PairsAbhik Bhattacharjee, Tahmid Hasan, Wasi Uddin Ahmad, Yuan-Fang Li et al.ACL 2023 · 23 citations
  4. MultiSumm: Towards a Unified Model for Multi-Lingual Abstractive SummarizationYue Cao, Xiaojun Wan, Jin-ge Yao, Dian YuAAAI 2020 · 28 citations
  5. ACROSS: An Alignment-based Framework for Low-Resource Many-to-One Cross-Lingual SummarizationPeiyao Li, Zhengkun Zhang, Jun Wang, Liang Li et al.ACL Findings 2023 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines