# WR-ONE2SET: Towards Well-Calibrated Keyphrase Generation

arXiv: https://arxiv.org/abs/2211.06862 · HTML: https://mlsanity.com/paper/2211.06862/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 13 Nov 2022.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Deep Keyphrase Generation](https://mlsanity.com/paper/1704.06879/) (2017)
- [Calibration of Encoder Decoder Models for Neural Machine Translation](https://mlsanity.com/paper/1903.00802/) (2019)
- [One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases](https://mlsanity.com/paper/1810.05241/) (2018)
- [Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards](https://mlsanity.com/paper/1906.04106/) (2019)
- [One2Set: Generating Diverse Keyphrases as a Set](https://mlsanity.com/paper/2105.11134/) (2021)
- [Exclusive Hierarchical Decoding for Deep Keyphrase Generation](https://mlsanity.com/paper/2004.08511/) (2020)
- [Title-Guided Encoding for Keyphrase Generation](https://mlsanity.com/paper/1808.08575/) (2018)
- [Variational Neural Machine Translation](https://mlsanity.com/paper/1605.07869/) (2016)
- [An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction](https://mlsanity.com/paper/1904.03454/) (2019)
- [Variational Recurrent Neural Machine Translation](https://mlsanity.com/paper/1801.05119/) (2018)
- [A Variational Hierarchical Model for Neural Cross-Lingual Summarization](https://mlsanity.com/paper/2203.03820/) (2022)
- [UniKeyphrase: A Unified Extraction and Generation Framework for Keyphrase Prediction](https://mlsanity.com/paper/2106.04847/) (2021)
- [Variational Neural Discourse Relation Recognizer](https://mlsanity.com/paper/1603.03876/) (2016)

## Built on by (most cited first, 13 of 13)

- [Is ChatGPT A Good Keyphrase Generator? A Preliminary Study](https://mlsanity.com/paper/2303.13001/) (2023)
- [A Sequence-to-Sequence&Set Model for Text-to-Table Generation](https://mlsanity.com/paper/2306.00137/) (2023)
- [From Statistical Methods to Deep Learning, Automatic Keyphrase Prediction: A Survey](https://mlsanity.com/paper/2305.02579/) (2023)
- [Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production](https://mlsanity.com/paper/2302.09300/) (2023)
- [SimCKP: Simple Contrastive Learning of Keyphrase Representations](https://mlsanity.com/paper/2310.08221/) (2023)
- [Pre-Trained Language Models for Keyphrase Prediction: A Review](https://mlsanity.com/paper/2409.01087/) (2024)
- [GraphEx: A Graph-based Extraction Method for Advertiser Keyphrase Recommendation](https://mlsanity.com/paper/2409.03140/) (2024)
- [One2set + Large Language Model: Best Partners for Keyphrase Generation](https://mlsanity.com/paper/2410.03421/) (2024)
- [Revisiting Non-Autoregressive Translation at Scale](https://mlsanity.com/paper/2305.16155/) (2023)
- [Towards Better Multi-modal Keyphrase Generation via Visual Entity Enhancement and Multi-granularity Image Noise Filtering](https://mlsanity.com/paper/2309.04734/) (2023)
- [LLMDistill4Ads: Using Cross-Encoders to Distill from LLM Signals for Advertiser Keyphrase Recommendations at eBay](https://mlsanity.com/paper/2508.03628/) (2025)
- [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)

Keyphrase generation aims to automatically generate short phrases summarizing an input document. The recently emerged ONE2SET paradigm (Ye et al., 2021) generates keyphrases as a set and has achieved competitive performance. Nevertheless, we observe serious calibration errors outputted by ONE2SET, especially in the over-estimation of varnothing token (means "no corresponding keyphrase"). In this paper, we deeply analyze this limitation and identify two main reasons behind: 1) the parallel generation has to introduce excessive varnothing as padding tokens into training instances; and 2) the training mechanism assigning target to each slot is unstable and further aggravates the varnothing token over-estimation. To make the model well-calibrated, we propose WR-ONE2SET which extends ONE2SET with an adaptive instance-level cost Weighting strategy and a target Re-assignment mechanism. The former dynamically penalizes the over-estimated slots for different instances thus smoothing the uneven training distribution. The latter refines the original inappropriate assignment and reduces the supervisory signals of over-estimated slots. Experimental results on commonly-used datasets demonstrate the effectiveness and generality of our proposed paradigm.