Papers with 1-shot

5 papers
Augmented Natural Language for Generative Sequence Labeling (2020.emnlp-main)

Copied to clipboard

Challenge: generative framework for joint sequence labeling and sentence-level classification is general purpose, performing well on few-shot learning, low resource, and high resource tasks.
Approach: They propose a generative framework for joint sequence labeling and sentence-level classification . their framework incorporates label semantics and shares knowledge across tasks .
Outcome: The proposed model performs on few-shot learning, slot labeling, and intent classification benchmarks.
PropaInsight: Toward Deeper Understanding of Propaganda in Terms of Techniques, Appeals, and Intent (2025.coling-main)

Copied to clipboard

Challenge: Existing research on propaganda detection does not capture the motives behind the content or its broader impact.
Approach: They propose a framework that dissects propaganda into techniques, arousal appeals, and underlying intent.
Outcome: The proposed framework improves performance in a wide range of scenarios and can be used to identify and categorize propaganda techniques.
TART: Improved Few-shot Text Classification Using Task-Adaptive Reference Transformation (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for fewshot text classification depend on inter-class variance . Existing approaches suffer from MLADA, which performs poorly on tasks with high inter- class variance whereas it fails to distinguish samples from tasks with low inter-group variance.
Approach: They propose a task-adaptive reference transformation network to transform class prototypes to per-class fixed reference points in task-adapted metric spaces.
Outcome: The proposed method surpasses state-of-the-art methods in 1-shot and 5-shot classifications on the 20 Newsgroups dataset.
PPTSER: A Plug-and-Play Tag-guided Method for Few-shot Semantic Entity Recognition on Visually-rich Documents (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods for visually-rich document information extraction are limited . Xu et al., 2020: visually rich document information is a vital aspect of document understanding .
Approach: They propose a plug-and-play Tag-guided method for few-shot Semantic Entity Recognition (PPTSER) on visually-rich documents.
Outcome: The proposed method outperforms fine-tuning and few-shot methods on visual-rich documents.
HomoGraphAdapter: A Homogeneous Graph Neural Network as an Effective Adapter for Vision-Language Models (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing adaptation methods overlook structural knowledge between text and image modalities or create overly complex graphs containing redundant information for alignment.
Approach: They propose a method to adapt visual models to downstream tasks using text and image modalities.
Outcome: The proposed method improves classification accuracy by 1.51% for 1-shot and 0.74% for 16-shot on 11 datasets.

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