SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.03235 · 2022

Pre-trained Token-replaced Detection Model as Few-shot Learner

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Pre-trained masked language models have demonstrated remarkable ability as few-shot learners. In this paper, as an alternative, we propose a novel approach to few-shot learning with pre-trained token-replaced detection models like ELECTRA. In this approach, we reformulate a classification or a regression task as a token-replaced detection problem. Specifically, we first define a template and label description words for each task and put them into the input to form a natural language prompt. Then, we employ the pre-trained token-replaced detection model to predict which label description word is the most original (i.e., least replaced) among all label description words in the prompt. A systematic evaluation on 16 datasets demonstrates that our approach outperforms few-shot learners with pre-trained masked language models in both one-sentence and two-sentence learning tasks.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2203.03235")
get_code_for_paper("2203.03235")
have("2203.03235")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2203.03235.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2203.03235.svg)](https://syntology.ai/paper/2203.03235)

Connect an agent — have() is free.