# Redefining Absent Keyphrases and their Effect on Retrieval Effectiveness

arXiv: https://arxiv.org/abs/2103.12440 · HTML: https://mlsanity.com/paper/2103.12440/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 53 references that are in the map.
- First posted on arXiv 23 Mar 2021.

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Pretrained Transformers for Text Ranking: BERT and Beyond](https://mlsanity.com/paper/2010.06467/) (2020)
- [Document Expansion by Query Prediction](https://mlsanity.com/paper/1904.08375/) (2019)
- [SemEval 2017 Task 10: ScienceIE - Extracting Keyphrases and Relations from Scientific Publications](https://mlsanity.com/paper/1704.02853/) (2017)
- [Deep Keyphrase Generation](https://mlsanity.com/paper/1704.06879/) (2017)
- [Unsupervised Keyphrase Extraction with Multipartite Graphs](https://mlsanity.com/paper/1803.08721/) (2018)
- [Keyphrase Generation with Correlation Constraints](https://mlsanity.com/paper/1808.07185/) (2018)
- [Exclusive Hierarchical Decoding for Deep Keyphrase Generation](https://mlsanity.com/paper/2004.08511/) (2020)
- [Citation Recommendation: Approaches and Datasets](https://mlsanity.com/paper/2002.06961/) (2020)
- [Open Domain Web Keyphrase Extraction Beyond Language Modeling](https://mlsanity.com/paper/1911.02671/) (2019)
- [Critically Examining the "Neural Hype": Weak Baselines and the Additivity of Effectiveness Gains from Neural Ranking Models](https://mlsanity.com/paper/1904.09171/) (2019)
- [DivGraphPointer: A Graph Pointer Network for Extracting Diverse Keyphrases](https://mlsanity.com/paper/1905.07689/) (2019)
- [Large-Scale Evaluation of Keyphrase Extraction Models](https://mlsanity.com/paper/2003.04628/) (2020)
- [Diverse Keyphrase Generation with Neural Unlikelihood Training](https://mlsanity.com/paper/2010.07665/) (2020)
- [Keyphrase Annotation with Graph Co-Ranking](https://mlsanity.com/paper/1611.02007/) (2016)

## Built on by (most cited first, 11 of 11)

- [Representation Learning for Resource-Constrained Keyphrase Generation](https://mlsanity.com/paper/2203.08118/) (2022)
- [Unsupervised Deep Keyphrase Generation](https://mlsanity.com/paper/2104.08729/) (2021)
- [KPDrop: Improving Absent Keyphrase Generation](https://mlsanity.com/paper/2112.01476/) (2021)
- [A Large-Scale Dataset for Biomedical Keyphrase Generation](https://mlsanity.com/paper/2211.12124/) (2022)
- [KPEval: Towards Fine-Grained Semantic-Based Keyphrase Evaluation](https://mlsanity.com/paper/2303.15422/) (2023)
- [Unsupervised Domain Adaptation for Keyphrase Generation using Citation Contexts](https://mlsanity.com/paper/2409.13266/) (2024)
- [On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation](https://mlsanity.com/paper/2402.14052/) (2024)
- [Self-Compositional Data Augmentation for Scientific Keyphrase Generation](https://mlsanity.com/paper/2411.03039/) (2024)
- [Neural Keyphrase Generation: Analysis and Evaluation](https://mlsanity.com/paper/2304.13883/) (2023)
- [An Analysis of Datasets, Metrics and Models in Keyphrase Generation](https://mlsanity.com/paper/2506.10346/) (2025)
- [Evaluating the Homogeneity of Keyphrase Prediction Models](https://mlsanity.com/paper/2602.12989/) (2026)

## 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.