Beyond prompting: Making Pre-trained Language Models Better Zero-shot Learners by Clustering Representations
Open Access
- 1 January 2022
- conference paper
- Published by Association for Computational Linguistics (ACL)
- p. 8560-8579
Abstract
Yu Fei, Zhao Meng, Ping Nie, Roger Wattenhofer, Mrinmaya Sachan. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language ProcessingACM Computing Surveys, 2023
- Making Pre-trained Language Models Better Few-shot Learners2021
- Discriminative Topic Mining via Category-Name Guided Text Embedding2020
- Text Classification Using Label Names Only: A Language Model Self-Training Approach2020
- Contextualized Weak Supervision for Text Classification2020
- Unsupervised Domain Clusters in Pretrained Language Models2020
- Self-Taught convolutional neural networks for short text clusteringNeural Networks, 2017
- Hidden factors and hidden topics2013
- How Close is the Sample Covariance Matrix to the Actual Covariance Matrix?Journal of Theoretical Probability, 2011
- Practical solutions to the problem of diagonal dominance in kernel document clustering2006