mlsanityData to 14 Oct 2026

KPDrop: Improving Absent Keyphrase Generation

arXiv 2112.01476 ↗First posted 2 Dec 2021cs.CLcited by 6

Not on the map. Why?

Abstract (arXiv)

Keyphrase generation is the task of generating phrases (keyphrases) that summarize the main topics of a given document. Keyphrases can be either present or absent from the given document. While the extraction of present keyphrases has received much attention in the past, only recently a stronger focus has been placed on the generation of absent keyphrases. However, generating absent keyphrases is challenging; even the best methods show only a modest degree of success. In this paper, we propose a model-agnostic approach called keyphrase dropout (or KPDrop) to improve absent keyphrase generation. In this approach, we randomly drop present keyphrases from the document and turn them into artificial absent keyphrases during training. We test our approach extensively and show that it consistently improves the absent performance of strong baselines in both supervised and resource-constrained semi-supervised settings.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 31 of its 70 references that are in the map. First posted on arXiv 2 Dec 2021.

Builds on

31 of 70 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2016Deep Networks with Stochastic Depthcited by 979
  4. 2019Reducing Transformer Depth on Demand with Structured Dropoutcited by 439
  5. 2017Deep Keyphrase Generationcited by 102
  6. 2018One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrasescited by 52
  7. 2018Unsupervised Keyphrase Extraction with Multipartite Graphscited by 50
  8. 2018Keyphrase Generation with Correlation Constraintscited by 45
  9. 2019Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewardscited by 41
  10. 2021One2Set: Generating Diverse Keyphrases as a Setcited by 41
  11. 2020Exclusive Hierarchical Decoding for Deep Keyphrase Generationcited by 38
  12. 2018Semi-Supervised Learning for Neural Keyphrase Generationcited by 36
19 more
  1. 2018Title-Guided Encoding for Keyphrase Generationcited by 36
  2. 2019Topic-Aware Neural Keyphrase Generation for Social Media Languagecited by 33
  3. 2019An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extractioncited by 28
  4. 2020An Empirical Study on Neural Keyphrase Generationcited by 25
  5. 2020Select, Extract and Generate: Neural Keyphrase Generation with Layer-wise Coverage Attentioncited by 24
  6. 2021Keyphrase Generation for Scientific Document Retrievalcited by 23
  7. 2021Unsupervised Keyphrase Extraction by Jointly Modeling Local and Global Contextcited by 17
  8. 2019DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrasescited by 16
  9. 2021Importance Estimation from Multiple Perspectives for Keyphrase Extractioncited by 16
  10. 2021UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Predictioncited by 15
  11. 2021Heterogeneous Graph Neural Networks for Keyphrase Generationcited by 15
  12. 2020Keyphrase Prediction With Pre-trained Language Modelcited by 13
  13. 2021Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learningcited by 13
  14. 2021Redefining Absent Keyphrases and their Effect on Retrieval Effectivenesscited by 11
  15. 2020SenSeNet: Neural Keyphrase Generation with Document Structurecited by 5
  16. 2020Keyphrase Generation with Cross-Document Attentioncited by 4
  17. 2021SGG: Learning to Select, Guide, and Generate for Keyphrase Generationcited by 4
  18. 2019Keyphrase Generation for Scientific Articles using GANscited by 3
  19. 2016Keyphrase Extraction using Sequential Labelingcited by 2

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 2.

6 papers.

  1. 2023Data Augmentation for Low-Resource Keyphrase Generationcited by 8
  2. 2023Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Modelscited by 8
  3. 2023SimCKP: Simple Contrastive Learning of Keyphrase Representationscited by 4
  4. 2023Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shufflingcited by 3
  5. 2024Pre-Trained Language Models for Keyphrase Prediction: A Reviewcited by 3
  6. 2024Self-Compositional Data Augmentation for Scientific Keyphrase Generationcited by 1