May 24, 2021 · We propose prompt tuning with rules (PTR) for many-class text classification and apply logic rules to construct prompts with several sub-prompts.

In this paper, we propose prompt tuning with rules (PTR) for many-class text classification tasks. By composing sub-prompts into task-specific prompts according ...

In this work, we propose prompt tuning with rules (PTR) for many-class text classification and apply logic rules to construct prompts with several sub-prompts.

Recently, prompt tuning has been widely applied to stimulate the rich knowledge in pre-trained language models (PLMs) to serve NLP tasks.

We propose prompt tuning with rules (PTR) for many-class text classification and apply logic rules to construct prompts with several sub-prompts.

This work explores “prompt tuning,” a simple yet effective mechanism for learning “soft prompts” to condition frozen language models to perform specific ...

Recently, prompt tuning has been widely applied to stimulate the rich knowledge in pre-trained language models (PLMs) to serve NLP tasks.

To this end, we propose prompt tuning with rules (PTR) for many-class text classification, and apply logic rules to construct prompts with several sub-prompts.

Prompts provide auxiliary information about what information to extract from pretrained models for specific tasks. It also often turns a classification task ...

PTR (Prompt Tuning with Rules) is a method for many-class text classification using PLMs. It constructs prompts using logic rules to encode prior knowledge ...