mlsanityData to 14 Oct 2026

Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training

arXiv 2205.10471 ↗First posted 21 May 2022cs.CL cs.AI cs.LGcited by 16

On the map: Retrieval-augmented generation → Generation and context integration

Abstract (arXiv)

Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text. Despite its recent flourishing, keyphrase generation on non-English languages haven't been vastly investigated. In this paper, we call attention to a new setting named multilingual keyphrase generation and we contribute two new datasets, EcommerceMKP and AcademicMKP, covering six languages. Technically, we propose a retrieval-augmented method for multilingual keyphrase generation to mitigate the data shortage problem in non-English languages. The retrieval-augmented model leverages keyphrase annotations in English datasets to facilitate generating keyphrases in low-resource languages. Given a non-English passage, a cross-lingual dense passage retrieval module finds relevant English passages. Then the associated English keyphrases serve as external knowledge for keyphrase generation in the current language. Moreover, we develop a retriever-generator iterative training algorithm to mine pseudo parallel passage pairs to strengthen the cross-lingual passage retriever. Comprehensive experiments and ablations show that the proposed approach outperforms all baselines.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 34 of its 62 references that are in the map. First posted on arXiv 21 May 2022.

Builds on

34 of 62 references.

Closest ancestors · 2

Same direction, newest first

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks22 May
  2. 2020REALM: Retrieval-Augmented Language Model Pre-Training10 Feb

Other references · 32

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2017Billion-scale similarity search with GPUscited by 2,497
  6. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  7. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  8. 2020Language-agnostic BERT Sentence Embeddingcited by 627
  9. 2020KILT: a Benchmark for Knowledge Intensive Language Taskscited by 573
  10. 2020Meta Pseudo Labelscited by 374
  11. 2021Case-based Reasoning for Natural Language Queries over Knowledge Basescited by 107
  12. 2017Deep Keyphrase Generationcited by 102
20 more
  1. 2018Margin-based Parallel Corpus Mining with Multilingual Sentence Embeddingscited by 83
  2. 2018Retrieve and Refine: Improved Sequence Generation Models For Dialoguecited by 82
  3. 2017Automated Phrase Mining from Massive Text Corporacited by 70
  4. 2021Neural Machine Translation with Monolingual Translation Memorycited by 61
  5. 2018Unsupervised Keyphrase Extraction with Multipartite Graphscited by 50
  6. 2018Keyphrase Generation with Correlation Constraintscited by 45
  7. 2019Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewardscited by 41
  8. 2019KPTimes: A Large-Scale Dataset for Keyphrase Generation on News Documentscited by 41
  9. 2021One2Set: Generating Diverse Keyphrases as a Setcited by 41
  10. 2020Exclusive Hierarchical Decoding for Deep Keyphrase Generationcited by 38
  11. 2018Semi-Supervised Learning for Neural Keyphrase Generationcited by 36
  12. 2018Title-Guided Encoding for Keyphrase Generationcited by 36
  13. 2019Topic-Aware Neural Keyphrase Generation for Social Media Languagecited by 33
  14. 2019An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extractioncited by 28
  15. 2020An Empirical Study on Neural Keyphrase Generationcited by 25
  16. 2020Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attentioncited by 24
  17. 2021Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Contextcited by 17
  18. 2021Heterogeneous Graph Neural Networks for Keyphrase Generationcited by 15
  19. 2021Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learningcited by 13
  20. 2020Keyphrase Extraction with Span-based Feature Representationscited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 2; 2023: 3; 2024: 7; 2025: 2; 2026: 2.

16 papers.

Sort:

By area:

  1. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 354
  2. 2024RAG and RAU: A Survey on Retrieval-Augmented Language Model in Natural Language Processingcited by 25
  3. 2024Shopping MMLU: A Massive Multi-Task Online Shopping Benchmark for Large Language Modelscited by 20
  4. 2022Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Studycited by 13
  5. 2025On the Consistency of Multilingual Context Utilization in Retrieval-Augmented Generationcited by 10
  6. 2024A Fine-tuning Enhanced RAG System with Quantized Influence Measure as AI Judgecited by 9
  7. 2023Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Modelscited by 8
  8. 2022General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generationcited by 5
  9. 2023Retrieval-Based Transformer for Table Augmentationcited by 3
  10. 2024On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generationcited by 3
  11. 2024Pre-Trained Language Models for Keyphrase Prediction: A Reviewcited by 3
  12. 2026All Languages Matter: Understanding and Mitigating Language Bias in Multilingual RAGcited by 3
4 more
  1. 2023RIGHT: Retrieval-augmented Generation for Mainstream Hashtag Recommendationcited by 2
  2. 2024Self-Compositional Data Augmentation for Scientific Keyphrase Generationcited by 1
  3. 2025An Analysis of Datasets, Metrics and Models in Keyphrase Generationcited by 0
  4. 2026SlovKE: A Large-Scale Dataset and LLM Evaluation for Slovak Keyphrase Extractioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024MetaKP: On-Demand Keyphrase Generation
  2. 2025Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Models
  3. 2022A Survey on Retrieval-Augmented Text Generation
  4. 2025Multilingual Retrieval-Augmented Generation for Knowledge-Intensive Task
  5. 2025Advancing Retrieval-Augmented Generation for Persian: Development of Language Models, Comprehensive Benchmarks, and Best Practices for Optimization
  6. 2025IterKey: Iterative Keyword Generation with LLMs for Enhanced Retrieval Augmented Generation
  7. 2024Retrieval is Accurate Generation
  8. 2024Retrieval-Augmented Machine Translation with Unstructured Knowledge