Weighted Training for Cross-Task Learning
Shuxiao Chen, Koby Crammer, Hangfeng He, Dan Roth, Weijie J Su
Abstract
In this paper, we introduce Target-Aware Weighted Training (TAWT), a weighted training algorithm for cross-task learning based on minimizing a representation-based task distance between the source and target tasks. We show that TAWT is easy to implement, is computationally efficient, requires little hyperparameter tuning, and enjoys non-asymptotic learning-theoretic guarantees. The effectiveness of TAWT is corroborated through extensive experiments with BERT on four sequence tagging tasks in natural language processing (NLP), including part-of-speech (PoS) tagging, chunking, predicate detection, and named entity recognition (NER). As a byproduct, the proposed representation-based task distance allows one to reason in a theoretically principled way about several critical aspects of cross-task learning, such as the choice of the source data and the impact of fine-tuning.
BibTeX
@inproceedings{
chen2022weighted,
title={Weighted Training for Cross-Task Learning},
author={Shuxiao Chen and Koby Crammer and Hangfeng He and Dan Roth and Weijie J Su},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=ltM1RMZntpu}
}