Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks

Fynn Schröder, Chris Biemann


Abstract
Multi-task learning (MTL) and transfer learning (TL) are techniques to overcome the issue of data scarcity when training state-of-the-art neural networks. However, finding beneficial auxiliary datasets for MTL or TL is a time- and resource-consuming trial-and-error approach. We propose new methods to automatically assess the similarity of sequence tagging datasets to identify beneficial auxiliary data for MTL or TL setups. Our methods can compute the similarity between any two sequence tagging datasets, they do not need to be annotated with the same tagset or multiple labels in parallel. Additionally, our methods take tokens and their labels into account, which is more robust than only using either of them as an information source, as conducted in prior work. We empirically show that our similarity measures correlate with the change in test score of neural networks that use the auxiliary dataset for MTL to increase the main task performance. We provide an efficient, open-source implementation.
Anthology ID:
2020.acl-main.268
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2971–2985
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.268
DOI:
10.18653/v1/2020.acl-main.268
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.268.pdf
Video:
 http://slideslive.com/38929002