Prototypical Verbalizer for Prompt-based Few-shot Tuning
Prompt-based tuning for pre-trained language models (PLMs) has shown its effectiveness in few-shot learning. Typically, prompt-based tuning wraps the input text into a cloze question. To make predictions, the model maps the output words to labels via a verbalizer, which is either manually designed or automatically built. However, manual verbalizers heavily depend on domain-specific prior knowledge and human efforts, while finding appropriate label words automatically still remains challenging.In this work, we propose the prototypical verbalizer (ProtoVerb) which is built directly from training data. Specifically, ProtoVerb learns prototype vectors as verbalizers by contrastive learning. In this way, the prototypes summarize training instances and are able to enclose rich class-level semantics. We conduct experiments on both topic classification and entity typing tasks, and the results demonstrate that ProtoVerb significantly outperforms current automatic verbalizers, especially when training data is extremely scarce. More surprisingly, ProtoVerb consistently boosts prompt-based tuning even on untuned PLMs, indicating an elegant non-tuning way to utilize PLMs.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningEntity TypingFew-Shot LearningTopic ClassificationSimilar Papers 제목 키워드 기반
Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer
Recent advances on prompt-tuning cast few-shot classification tasks as a masked language modeling problem. By wrapping input into a template and using a verbalizer which constructs a mapping between label space and label…
ClassificationContrastive LearningLanguage ModelingLanguage Modelling+3Prototypical Verbalizer for Prompt-based Few-shot Tuning
Prompt-based tuning for pre-trained language models (PLMs) has shown its effectiveness in few-shot learning. Typically, prompt-based tuning wraps the input text into a cloze question. To make predictions, the model maps …
Contrastive LearningEntity TypingFew-Shot LearningTopic ClassificationEvolutionary Verbalizer Search for Prompt-based Few Shot Text Classification
Recent advances for few-shot text classification aim to wrap textual inputs with task-specific prompts to cloze questions. By processing them with a masked language model to predict the masked tokens and using a verbaliz…
Few-Shot Text ClassificationLanguage ModelingLanguage Modellingtext-classification+1Scalable Prompt Generation for Semi-supervised Learning with Language Models
Prompt-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 …
Few-Shot LearningNatural Language UnderstandingKnowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification
Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification. Particularly, previous studies suggest that prompt-tuning has remarkable superiority in the low-…
Few-Shot Text ClassificationLanguage ModelingLanguage ModellingMasked Language Modeling+2