Efficient Active Learning for Imbalanced Datasets: AnchorAL Approach
AnchorAL is a computationally efficient active learning method that addresses class imbalance by dynamically selecting a small, balanced subpool of instances to run the active learning strategy on, promoting the discovery of minority instances.
Enhancing Plausibility of Text Classifier Explanations Using Human Rationales
Incorporating human-annotated rationales into text classification models enhances the plausibility of post-hoc explanations without substantially degrading model performance.
The Profound Impact of Prompt Variations on Large Language Model Predictions
Even minor changes to prompts can significantly alter the predictions of large language models, with some variations leading to substantial performance degradation.
RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules
텍스트 분류를 위한 RulePrompt 방법은 PLM과 논리 규칙을 활용하여 효과적으로 분류 성능을 향상시킵니다.
Demonstration of Mutual Reinforcement Effect through Information Flow in Text Classification Tasks
Die Mutual Reinforcement Effect (MRE) Theorie wird durch Information Flow Analyse in Textklassifikationsaufgaben bestätigt.
TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision
TELEClass verbessert die hierarchische Textklassifizierung durch Taxonomieanreicherung und LLM-Verbesserung.
TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision
Hierarchical text classification with minimal supervision using Taxonomy Enrichment and LLM enhancement.
TELEClass: Taxonomy Enrichment and LLM-Enhanced Hierarchical Text Classification with Minimal Supervision
Hierarchical text classification with minimal supervision using taxonomy enrichment and LLM enhancement.
RulePrompt: Weakly Supervised Text Classification with Prompting PLMs and Self-Iterative Logical Rules
The authors propose RulePrompt, a novel approach that leverages logical rules to enhance the understanding of categories in weakly supervised text classification tasks using prompting PLMs.
Margin Discrepancy-based Adversarial Training for Multi-Domain Text Classification Analysis
The author analyzes the Margin Discrepancy-based Adversarial Training approach for Multi-Domain Text Classification, providing theoretical underpinnings and empirical validation.
© 2024 by Linnk AI