COBART: Controlled, Optimized, Bidirectional and Auto-Regressive Transformer for Ad Headline Generation
Not on the map. Why?
Abstract (arXiv)
Online ads are essential to all businesses and ad headlines are one of their core creative component. Existing methods can generate headlines automatically and also optimize their click-through-rate (CTR) and quality. However, evolving ad formats and changing creative requirements make it difficult to generate optimized & customized headlines. We propose a novel method that uses prefix control tokens along with BART fine-tuning. It yields the highest CTR and also allows users to control the length of generated headlines for use across different ad formats. The method is also flexible and can easily be adapted to other architectures, creative requirements and optimization criteria. Our experiments demonstrate a 25.82% increment in Rouge-L and a 5.82% increment in estimated CTR over previously published strong ad headline generation baseline.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 33 references that are in the map. First posted on arXiv 9 Jul 2026.
Builds on
27 of 33 references.
References · 27
- 2017Attention Is All You Needcited by 59,932
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2020Language Models are Few-Shot Learnerscited by 32,199
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
- 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,201
- 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
- 2019Plug and Play Language Models: A Simple Approach to Controlled Text Generationcited by 793
- 2019CTRL: A Conditional Transformer Language Model for Controllable Generationcited by 754
- 2019Unified Language Model Pre-training for Natural Language Understanding and Generationcited by 668
- 2016Self-critical Sequence Training for Image Captioningcited by 544
15 more
- 2021FUDGE: Controlled Text Generation With Future Discriminatorscited by 374
- 2019MASS: Masked Sequence to Sequence Pre-training for Language Generationcited by 345
- 2017Toward Controlled Generation of Textcited by 271
- 2020ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-trainingcited by 221
- 2019Leveraging Pre-trained Checkpoints for Sequence Generation Taskscited by 182
- 2021ExT5: Towards Extreme Multi-Task Scaling for Transfer Learningcited by 161
- 2018Correcting Length Bias in Neural Machine Translationcited by 119
- 2021Controlled Text Generation as Continuous Optimization with Multiple Constraintscited by 70
- 2020Hooks in the Headline: Learning to Generate Headlines with Controlled Stylescited by 46
- 2019Clickbait? Sensational Headline Generation with Auto-tuned Reinforcement Learningcited by 19
- 2019Self-Attentive Model for Headline Generationcited by 16
- 2018Texar: A Modularized, Versatile, and Extensible Toolkit for Text Generationcited by 13
- 2020Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generationcited by 12
- 2021VAE based Text Style Transfer with Pivot Words Enhancement Learningcited by 4
- 2026Ad Headline Generation using Self-Critical Masked Language Modelcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.