@inproceedings{deb-etal-2022-post,
title = "Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines",
author = "Deb, Kiron and
Zhang, Xuan and
Duh, Kevin",
editor = "Bastings, Jasmijn and
Belinkov, Yonatan and
Elazar, Yanai and
Hupkes, Dieuwke and
Saphra, Naomi and
Wiegreffe, Sarah",
booktitle = "Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates (Hybrid)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.blackboxnlp-1.5",
doi = "10.18653/v1/2022.blackboxnlp-1.5",
pages = "51--61",
abstract = "Hyperparameter tuning is important for achieving high accuracy in deep learning models, yet little interpretability work has focused on hyperparameters. We propose to use the Explainable Boosting Machine (EBM), a glassbox method, as a post-hoc analysis tool for understanding how hyperparameters influence model accuracy. We present a case study on Transformer models in machine translation to illustrate the kinds of insights that may be gleaned, and perform extensive analysis to test the robustness of EBM under different data conditions.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="deb-etal-2022-post">
<titleInfo>
<title>Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kiron</namePart>
<namePart type="family">Deb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jasmijn</namePart>
<namePart type="family">Bastings</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonatan</namePart>
<namePart type="family">Belinkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanai</namePart>
<namePart type="family">Elazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naomi</namePart>
<namePart type="family">Saphra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Wiegreffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates (Hybrid)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Hyperparameter tuning is important for achieving high accuracy in deep learning models, yet little interpretability work has focused on hyperparameters. We propose to use the Explainable Boosting Machine (EBM), a glassbox method, as a post-hoc analysis tool for understanding how hyperparameters influence model accuracy. We present a case study on Transformer models in machine translation to illustrate the kinds of insights that may be gleaned, and perform extensive analysis to test the robustness of EBM under different data conditions.</abstract>
<identifier type="citekey">deb-etal-2022-post</identifier>
<identifier type="doi">10.18653/v1/2022.blackboxnlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2022.blackboxnlp-1.5</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>51</start>
<end>61</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines
%A Deb, Kiron
%A Zhang, Xuan
%A Duh, Kevin
%Y Bastings, Jasmijn
%Y Belinkov, Yonatan
%Y Elazar, Yanai
%Y Hupkes, Dieuwke
%Y Saphra, Naomi
%Y Wiegreffe, Sarah
%S Proceedings of the Fifth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates (Hybrid)
%F deb-etal-2022-post
%X Hyperparameter tuning is important for achieving high accuracy in deep learning models, yet little interpretability work has focused on hyperparameters. We propose to use the Explainable Boosting Machine (EBM), a glassbox method, as a post-hoc analysis tool for understanding how hyperparameters influence model accuracy. We present a case study on Transformer models in machine translation to illustrate the kinds of insights that may be gleaned, and perform extensive analysis to test the robustness of EBM under different data conditions.
%R 10.18653/v1/2022.blackboxnlp-1.5
%U https://aclanthology.org/2022.blackboxnlp-1.5
%U https://doi.org/10.18653/v1/2022.blackboxnlp-1.5
%P 51-61
Markdown (Informal)
[Post-Hoc Interpretation of Transformer Hyperparameters with Explainable Boosting Machines](https://aclanthology.org/2022.blackboxnlp-1.5) (Deb et al., BlackboxNLP 2022)
ACL