Papers with auxiliary multi-task
Disentangled Representation Learning for Non-Parallel Text Style Transfer (P19-1)
Copied to clipboard
| Challenge: | a paper aims to disentangle latent representations of style and content in language models . auxiliary multi-task and adversarial objectives are used to disentangle the latent space . |
| Approach: | They propose a simple yet effective approach to disentangling latent representations . they propose auxiliary multi-task and adversarial objectives to disentangle style and content . |
| Outcome: | The proposed approach achieves high performance in terms of transfer accuracy, content preservation, and language fluency compared to previous approaches . |
MediaHG: Rethinking Eye-catchy Features in Social Media Headline Generation (2023.emnlp-main)
Copied to clipboard
| Challenge: | Creating a good headline on social media platforms requires a disentanglement-based model to balance the content and contextual features. |
| Approach: | They propose a disentanglement-based headline generation model which can balance the content and contextual features by incorporating contrastive learning and auxiliary multi-tasking to choose the best domain-suitable headline. |
| Outcome: | The proposed model can balance content and contextual features, while allowing bloggers to obtain more site traffic and profits while readers can have easier access to topics of interest. |