mlsanityData to 14 Oct 2026

Learning Rich Representation of Keyphrases from Text

arXiv 2112.08547 ↗First posted 16 Dec 2021cs.CL cs.IR cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

In this work, we explore how to train task-specific language models aimed towards learning rich representation of keyphrases from text documents. We experiment with different masking strategies for pre-training transformer language models (LMs) in discriminative as well as generative settings. In the discriminative setting, we introduce a new pre-training objective - Keyphrase Boundary Infilling with Replacement (KBIR), showing large gains in performance (upto 8.16 points in F1) over SOTA, when the LM pre-trained using KBIR is fine-tuned for the task of keyphrase extraction. In the generative setting, we introduce a new pre-training setup for BART - KeyBART, that reproduces the keyphrases related to the input text in the CatSeq format, instead of the denoised original input. This also led to gains in performance (upto 4.33 points in F1@M) over SOTA for keyphrase generation. Additionally, we also fine-tune the pre-trained language models on named entity recognition (NER), question answering (QA), relation extraction (RE), abstractive summarization and achieve comparable performance with that of the SOTA, showing that learning rich representation of keyphrases is indeed beneficial for many other fundamental NLP tasks.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 43 of its 74 references that are in the map. First posted on arXiv 16 Dec 2021.

Builds on

43 of 74 references.

References · 43

  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. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  4. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,893
  5. 2016Layer Normalizationcited by 5,669
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  7. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  8. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,790
  9. 2018Deep contextualized word representationscited by 2,290
  10. 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
  11. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,102
  12. 2015Teaching Machines to Read and Comprehendcited by 1,049
31 more
  1. 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 834
  2. 2016Neural Architectures for Named Entity Recognitioncited by 550
  3. 2019ERNIE: Enhanced Language Representation with Informative Entitiescited by 528
  4. 2019Quantifying the Carbon Emissions of Machine Learningcited by 521
  5. 2020Pre-trained Models for Natural Language Processing: A Surveycited by 505
  6. 2019KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representationcited by 356
  7. 2020LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attentioncited by 326
  8. 2020K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapterscited by 319
  9. 2019Knowledge Enhanced Contextual Word Representationscited by 296
  10. 2019Matching the Blanks: Distributional Similarity for Relation Learningcited by 272
  11. 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
  12. 2017SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publicationscited by 102
  13. 2017Deep Keyphrase Generationcited by 102
  14. 2019Pretrained Encyclopedia: Weakly Supervised Knowledge-Pretrained Language Modelcited by 102
  15. 2021An Improved Baseline for Sentence-level Relation Extractioncited by 81
  16. 2018One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrasescited by 52
  17. 2018Keyphrase Generation with Correlation Constraintscited by 45
  18. 2019Cloze-driven Pretraining of Self-attention Networkscited by 41
  19. 2019Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewardscited by 41
  20. 2021One2Set: Generating Diverse Keyphrases as a Setcited by 41
  21. 2020Exclusive Hierarchical Decoding for Deep Keyphrase Generationcited by 38
  22. 2018Semi-Supervised Learning for Neural Keyphrase Generationcited by 36
  23. 2018Title-Guided Encoding for Keyphrase Generationcited by 36
  24. 2020An Empirical Study on Neural Keyphrase Generationcited by 25
  25. 2020TNT-KID: Transformer-based Neural Tagger for Keyword Identificationcited by 15
  26. 2019Keyphrase Extraction from Scholarly Articles as Sequence Labeling using Contextualized Embeddingscited by 14
  27. 2020Keyphrase Prediction With Pre-trained Language Modelcited by 13
  28. 2019Keyphrase Generation: A Text Summarization Strugglecited by 12
  29. 2019S2ORC: The Semantic Scholar Open Research Corpuscited by 10
  30. 2020Two Huge Title and Keyword Generation Corpora of Research Articlescited by 10
  31. 2019Keyphrase Generation: A Multi-Aspect Surveycited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 5; 2023: 16; 2024: 9; 2025: 3; 2026: 3.

36 papers.

Sort:

By area:

  1. 2023A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Validating Low-Confidence Generationcited by 206
  2. 2023A Survey of GPT-3 Family Large Language Models Including ChatGPT and GPT-4cited by 81
  3. 2022Nonparametric Masked Language Modelingcited by 40
  4. 2022Representation Learning for Resource-Constrained Keyphrase Generationcited by 14
  5. 2023From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Surveycited by 14
  6. 2022LDKP: A Dataset for Identifying Keyphrases from Long Scientific Documentscited by 13
  7. 2022Pre-trained Language Models for Keyphrase Generation: A Thorough Empirical Studycited by 13
  8. 2023ChatGPT vs State-of-the-Art Models: A Benchmarking Study in Keyphrase Generation Taskcited by 13
  9. 2023Data Augmentation for Low-Resource Keyphrase Generationcited by 8
  10. 2023Rethinking Model Selection and Decoding for Keyphrase Generation with Pre-trained Sequence-to-Sequence Modelscited by 8
  11. 2023A Cross Attention Approach to Diagnostic Explainability using Clinical Practice Guidelines for Depressioncited by 8
  12. 2022General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generationcited by 5
24 more
  1. 2024EUROPA: A Legal Multilingual Keyphrase Generation Datasetcited by 5
  2. 2023KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluationcited by 4
  3. 2023SimCKP: Simple Contrastive Learning of Keyphrase Representationscited by 4
  4. 2024Unsupervised Domain Adaptation for Keyphrase Generation using Citation Contextscited by 4
  5. 2023Enhancing Keyphrase Extraction from Long Scientific Documents using Graph Embeddingscited by 3
  6. 2023Text Simplification of Scientific Texts for Non-Expert Readerscited by 3
  7. 2023Enhancing Keyphrase Generation by BART Finetuning with Splitting and Shufflingcited by 3
  8. 2023LLMs Perform Poorly at Concept Extraction in Cyber-security Research Literaturecited by 3
  9. 2024On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generationcited by 3
  10. 2024Pre-Trained Language Models for Keyphrase Prediction: A Reviewcited by 3
  11. 2023Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extractioncited by 2
  12. 2024Generating Attractive and Authentic Copywriting from Customer Reviewscited by 2
  13. 2024Deep Knowledge-Infusion For Explainable Depression Detectioncited by 2
  14. 2024Exploring Fine-tuned Generative Models for Keyphrase Selection: A Case Study for Russiancited by 1
  15. 2024Self-Compositional Data Augmentation for Scientific Keyphrase Generationcited by 1
  16. 2023Neural Keyphrase Generation: Analysis and Evaluationcited by 0
  17. 2023Cross-Domain Robustness of Transformer-based Keyphrase Generationcited by 0
  18. 2024MetaKP: On-Demand Keyphrase Generationcited by 0
  19. 2025Zero-Shot Keyphrase Generation: Investigating Specialized Instructions and Multi-Sample Aggregation on Large Language Modelscited by 0
  20. 2025An Analysis of Datasets, Metrics and Models in Keyphrase Generationcited by 0
  21. 2025THM@SimpleText 2025 -- Task 1.1: Revisiting Text Simplification based on Complex Terms for Non-Expertscited by 0
  22. 2026Evaluating the Homogeneity of Keyphrase Prediction Modelscited by 0
  23. 2026Explaining Black-Box Language Models: Learning to Optimize Linguistically-Structured Word Subsetscited by 0
  24. 2026Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddingscited by 0