@inproceedings{schroder-biemann-2020-estimating,
title = "Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks",
author = {Schr{\"o}der, Fynn and
Biemann, Chris},
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.268",
doi = "10.18653/v1/2020.acl-main.268",
pages = "2971--2985",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schroder-biemann-2020-estimating">
<titleInfo>
<title>Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fynn</namePart>
<namePart type="family">Schröder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Biemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-jul</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">schroder-biemann-2020-estimating</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.268</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.268</url>
</location>
<part>
<date>2020-jul</date>
<extent unit="page">
<start>2971</start>
<end>2985</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks
%A Schröder, Fynn
%A Biemann, Chris
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 jul
%I Association for Computational Linguistics
%C Online
%F schroder-biemann-2020-estimating
%X 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.
%R 10.18653/v1/2020.acl-main.268
%U https://aclanthology.org/2020.acl-main.268
%U https://doi.org/10.18653/v1/2020.acl-main.268
%P 2971-2985
Markdown (Informal)
[Estimating the influence of auxiliary tasks for multi-task learning of sequence tagging tasks](https://aclanthology.org/2020.acl-main.268) (Schröder & Biemann, ACL 2020)
ACL