Обучение на основе подсказок
Related Papers
Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification
AbstractPrompt-based learning (i.e., prompting) is an emerging paradigm for exploiting knowledge learned by a pretrained language model. In this paper, we propose Automatic Multi-Label Prompting (AMuLaP), a simple yet effective …...
Decorate the Examples: A Simple Method of Prompt Design for Biomedical Relation Extraction
AbstractRelation extraction is a core problem for natural language processing in the biomedical domain. Recent research on relation extraction showed that prompt-based learning improves the performance on both fine-tuning on …...
DESED: Dialogue-based Explanation for Sentence-level Event Detection
AbstractMany recent sentence-level event detection efforts focus on enriching sentence semantics, e.g., via multi-task or prompt-based learning. Despite the promising performance, these methods commonly depend on label-extensive manual annotations or …...
Good Examples Make A Faster Learner: Simple Demonstration-based Learning for Low-resource NER
AbstractRecent advances in prompt-based learning have shown strong results on few-shot text classification by using cloze-style templates. Similar attempts have been made on named entity recognition (NER) which manually design …...
Learning to Transfer Prompts for Text Generation
AbstractPretrained language models (PLMs) have made remarkable progress in text generation tasks via fine-tuning. While, it is challenging to fine-tune PLMs in a data-scarce situation. Therefore, it is non-trivial to …...
Prompt-based Distribution Alignment for Domain Generalization in Text Classification
AbstractPrompt-based learning (a.k.a. prompting) achieves high performance by bridging the gap between the objectives of language modeling and downstream tasks. Domain generalization ability can be improved by prompting since classification …...
Prompting ELECTRA: Few-Shot Learning with Discriminative Pre-Trained Models
AbstractPre-trained masked language models successfully perform few-shot learning by formulating downstream tasks as text infilling. How- ever, as a strong alternative in full-shot settings, discriminative pre-trained models like ELECTRA do …...
Cold-Start Data Selection for Better Few-shot Language Model Fine-tuning: A Prompt-based Uncertainty Propagation Approach
AbstractWe present PATRON, a prompt-based data selection method for pre-trained language model fine-tuning under cold-start scenarios, i.e., no initial labeled data are available. In PATRON, we design (1) a prompt-based …...
Hierarchical Verbalizer for Few-Shot Hierarchical Text Classification
AbstractDue to the complex label hierarchy and intensive labeling cost in practice, the hierarchical text classification (HTC) suffers a poor performance especially when low-resource or few-shot settings are considered. Recently, …...
L3I++ at SemEval-2023 Task 2: Prompting for Multilingual Complex Named Entity Recognition
AbstractThis paper summarizes the participation of the L3i laboratory of the University of La Rochelle in the SemEval-2023 Task 2, Multilingual Complex Named Entity Recognition (MultiCoNER II). Similar to MultiCoNER …...
Scalable Prompt Generation for Semi-supervised Learning with Language Models
AbstractPrompt-based learning methods in semi-supervised learning (SSL) settings have been shown to be effective on multiple natural language understanding (NLU) datasets and tasks in the literature. However, manually designing multiple …...