Papers with meta-learning baselines

2 papers
Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection (2021.naacl-main)

Copied to clipboard

Challenge: Existing datasets for sarcasm detection are limited due to the difficulty in acquiring ground-truth annotations.
Approach: They propose a generalized latent optimization strategy that allows different losses to accommodate each other and improves training dynamics.
Outcome: The proposed approach outperforms transfer learning and meta-learning baselines and achieves 10.02% performance gain on the iSarcasm dataset.
On Task-personalized Multimodal Few-shot Learning for Visually-rich Document Entity Retrieval (2023.findings-emnlp)

Copied to clipboard

Challenge: Visually-rich document entity retrieval (VDER) is an important topic in industrial NLP applications.
Approach: They propose a task-aware meta-learning framework to tackle the problem of visually-rich document entity retrieval (VDER) they adopt a hierarchical decoder and employ contrastive learning to achieve this goal.
Outcome: The proposed framework significantly improves the robustness of popular meta-learning baselines.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations