@inproceedings{feldhus-etal-2021-thermostat,
title = "Thermostat: A Large Collection of {NLP} Model Explanations and Analysis Tools",
author = {Feldhus, Nils and
Schwarzenberg, Robert and
M{\"o}ller, Sebastian},
editor = "Adel, Heike and
Shi, Shuming",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-demo.11",
doi = "10.18653/v1/2021.emnlp-demo.11",
pages = "87--95",
abstract = "In the language domain, as in other domains, neural explainability takes an ever more important role, with feature attribution methods on the forefront. Many such methods require considerable computational resources and expert knowledge about implementation details and parameter choices. To facilitate research, we present Thermostat which consists of a large collection of model explanations and accompanying analysis tools. Thermostat allows easy access to over 200k explanations for the decisions of prominent state-of-the-art models spanning across different NLP tasks, generated with multiple explainers. The dataset took over 10k GPU hours ({\textgreater} one year) to compile; compute time that the community now saves. The accompanying software tools allow to analyse explanations instance-wise but also accumulatively on corpus level. Users can investigate and compare models, datasets and explainers without the need to orchestrate implementation details. Thermostat is fully open source, democratizes explainability research in the language domain, circumvents redundant computations and increases comparability and replicability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feldhus-etal-2021-thermostat">
<titleInfo>
<title>Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Feldhus</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Schwarzenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Adel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuming</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the language domain, as in other domains, neural explainability takes an ever more important role, with feature attribution methods on the forefront. Many such methods require considerable computational resources and expert knowledge about implementation details and parameter choices. To facilitate research, we present Thermostat which consists of a large collection of model explanations and accompanying analysis tools. Thermostat allows easy access to over 200k explanations for the decisions of prominent state-of-the-art models spanning across different NLP tasks, generated with multiple explainers. The dataset took over 10k GPU hours (\textgreater one year) to compile; compute time that the community now saves. The accompanying software tools allow to analyse explanations instance-wise but also accumulatively on corpus level. Users can investigate and compare models, datasets and explainers without the need to orchestrate implementation details. Thermostat is fully open source, democratizes explainability research in the language domain, circumvents redundant computations and increases comparability and replicability.</abstract>
<identifier type="citekey">feldhus-etal-2021-thermostat</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-demo.11</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-demo.11</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>87</start>
<end>95</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools
%A Feldhus, Nils
%A Schwarzenberg, Robert
%A Möller, Sebastian
%Y Adel, Heike
%Y Shi, Shuming
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F feldhus-etal-2021-thermostat
%X In the language domain, as in other domains, neural explainability takes an ever more important role, with feature attribution methods on the forefront. Many such methods require considerable computational resources and expert knowledge about implementation details and parameter choices. To facilitate research, we present Thermostat which consists of a large collection of model explanations and accompanying analysis tools. Thermostat allows easy access to over 200k explanations for the decisions of prominent state-of-the-art models spanning across different NLP tasks, generated with multiple explainers. The dataset took over 10k GPU hours (\textgreater one year) to compile; compute time that the community now saves. The accompanying software tools allow to analyse explanations instance-wise but also accumulatively on corpus level. Users can investigate and compare models, datasets and explainers without the need to orchestrate implementation details. Thermostat is fully open source, democratizes explainability research in the language domain, circumvents redundant computations and increases comparability and replicability.
%R 10.18653/v1/2021.emnlp-demo.11
%U https://aclanthology.org/2021.emnlp-demo.11
%U https://doi.org/10.18653/v1/2021.emnlp-demo.11
%P 87-95
Markdown (Informal)
[Thermostat: A Large Collection of NLP Model Explanations and Analysis Tools](https://aclanthology.org/2021.emnlp-demo.11) (Feldhus et al., EMNLP 2021)
ACL