Papers with domain generalization ability

4 papers
Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs (2023.acl-industry)

Copied to clipboard

Challenge: Existing methods to dialog quality estimation focus on evaluating individual turns or collecting dialog-level quality measurements from end users immediately following an interaction.
Approach: They propose a dialog-level annotation workflow called Dialog Quality Annotation . they propose to annotate dialogs for attributes such as goal completion and user sentiment .
Outcome: The proposed model outperforms existing methods for dialog quality estimation . it shows that high-quality human-annotated data is important for dialog-quality evaluation .
Self-supervised Meta-Prompt Learning with Meta-Gradient Regularization for Few-shot Generalization (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing methods for prompt tuning can overfit to few-shot training samples, causing overfitting . authors propose a new framework for prompt learning with supervised meta-learning .
Approach: They propose a self-supervised meta-prompt learning framework with MEta-gradient Regularization for few-shot generalization that leverages self-recognized meta-learning with a diverse set of meta-tasks to learn a universal prompt initialization using only unlabeled data.
Outcome: The proposed framework learns a universal prompt initialization for efficient adaptation using only unlabeled data.
Exploiting domain-slot related keywords description for Few-Shot Cross-Domain Dialogue State Tracking (2022.emnlp-main)

Copied to clipboard

Challenge: Existing frameworks for dialogue state tracking with domain-slot-value labels are expensive . current models are limited due to high cost of data annotation and lack of data in some domains .
Approach: They propose a framework based on domain-slot related description to tackle the challenge of few-shot cross-domain DST.
Outcome: The proposed framework outperforms existing methods on MultiWOZ and gains strong slot accuracy compared to existing models.
Efficient Cross-modal Prompt Learning with Semantic Enhancement for Domain-robust Fake News Detection (2025.coling-main)

Copied to clipboard

Challenge: Existing MFND methods conduct cross-modal information interaction at later stage, resulting in weak generalization ability.
Approach: They propose an automatic multi-modal fake news detection method that exploits cross-modal information interaction at later stage.
Outcome: The proposed method outperforms state-of-the-art methods on three MFND benchmarks.

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