Verbalizer
Last updated on November 12, 2024
In the classification setting, verbalizers are mappings from labels to words in a language model's vocabulary. For example, consider performing sentiment classification with the following prompt:
Prompt
Tweet: "I love hot pockets" What is the sentiment of this tweet? Say 'pos' or 'neg'.
Here, the verbalizer is the mapping from the conceptual labels of positive and negative to the tokens pos and neg.
Footnotes
-
Schick, T., & Schütze, H. (2020). Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference. ↩
