Подсказки
Related Papers
A Two Stage Adaptation Framework for Frame Detection via Prompt Learning
AbstractFraming is a communication strategy to bias discussion by selecting and emphasizing. Frame detection aims to automatically analyze framing strategy. Previous works on frame detection mainly focus on a single …...
Bi-Directional Iterative Prompt-Tuning for Event Argument Extraction
AbstractRecently, prompt-tuning has attracted growing interests in event argument extraction (EAE). However, the existing prompt-tuning methods have not achieved satisfactory performance due to the lack of consideration of entity information. …...
Learning To Retrieve Prompts for In-Context Learning
AbstractIn-context learning is a recent paradigm in natural language understanding, where a large pre-trained language model (LM) observes a test instance and a few training examples as its input, and …...
A Practical Survey on Zero-Shot Prompt Design for In-Context Learning
AbstractThe remarkable advancements in large language models (LLMs) have brought about significant improvements in Natural Language Processing(NLP) tasks. This paper presents a comprehensive review of in-context learning techniques, focusing on …...