mlsanityData to 7 Oct 2026

Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness

arXiv 2103.12440 ↗First posted 23 Mar 2021cs.IR cs.CLcited by 11

Not on the map. Why?

Abstract (arXiv)

Neural keyphrase generation models have recently attracted much interest due to their ability to output absent keyphrases, that is, keyphrases that do not appear in the source text. In this paper, we discuss the usefulness of absent keyphrases from an Information Retrieval (IR) perspective, and show that the commonly drawn distinction between present and absent keyphrases is not made explicit enough. We introduce a finer-grained categorization scheme that sheds more light on the impact of absent keyphrases on scientific document retrieval. Under this scheme, we find that only a fraction (around 20%) of the words that make up keyphrases actually serves as document expansion, but that this small fraction of words is behind much of the gains observed in retrieval effectiveness. We also discuss how the proposed scheme can offer a new angle to evaluate the output of neural keyphrase generation models.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 15 of its 53 references that are in the map. First posted on arXiv 23 Mar 2021.

Builds on

15 of 53 references.

References · 15

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Pretrained Transformers for Text Ranking: BERT and Beyondcited by 266
  3. 2019Document Expansion by Query Predictioncited by 225
  4. 2017Deep Keyphrase Generationcited by 102
  5. 2017SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publicationscited by 101
  6. 2018Unsupervised Keyphrase Extraction with Multipartite Graphscited by 50
  7. 2018Keyphrase Generation with Correlation Constraintscited by 45
  8. 2020Exclusive Hierarchical Decoding for Deep Keyphrase Generationcited by 38
  9. 2020Citation Recommendation: Approaches and Datasetscited by 36
  10. 2019Open Domain Web Keyphrase Extraction Beyond Language Modelingcited by 28
  11. 2019Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Modelscited by 24
  12. 2019DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrasescited by 16
3 more
  1. 2020Large-Scale Evaluation of Keyphrase Extraction Modelscited by 8
  2. 2020Diverse Keyphrase Generation with Neural Unlikelihood Trainingcited by 7
  3. 2016Keyphrase Annotation with Graph Co-Rankingcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 2; 2024: 3; 2025: 1; 2026: 1.

11 papers.

  1. 2022Representation Learning for Resource-Constrained Keyphrase Generationcited by 14
  2. 2021Unsupervised Deep Keyphrase Generationcited by 7
  3. 2021KPDrop: Improving Absent Keyphrase Generationcited by 6
  4. 2022A Large-Scale Dataset for Biomedical Keyphrase Generationcited by 6
  5. 2023KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluationcited by 4
  6. 2024Unsupervised Domain Adaptation for Keyphrase Generation using Citation Contextscited by 4
  7. 2024On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generationcited by 3
  8. 2024Self-Compositional Data Augmentation for Scientific Keyphrase Generationcited by 1
  9. 2023Neural Keyphrase Generation: Analysis and Evaluationcited by 0
  10. 2025An Analysis of Datasets, Metrics and Models in Keyphrase Generationcited by 0
  11. 2026Evaluating the Homogeneity of Keyphrase Prediction Modelscited by 0