@inproceedings{gralinski-etal-2019-geval,
title = "{GE}val: Tool for Debugging {NLP} Datasets and Models",
author = "Grali{\'n}ski, Filip and
Wr{\'o}blewska, Anna and
Stanis{\l}awek, Tomasz and
Grabowski, Kamil and
G{\'o}recki, Tomasz",
editor = "Linzen, Tal and
Chrupa{\l}a, Grzegorz and
Belinkov, Yonatan and
Hupkes, Dieuwke",
booktitle = "Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-4826",
doi = "10.18653/v1/W19-4826",
pages = "254--262",
abstract = "This paper presents a simple but general and effective method to debug the output of machine learning (ML) supervised models, including neural networks. The algorithm looks for features that lower the evaluation metric in such a way that it cannot be ascribed to chance (as measured by their p-values). Using this method {--} implemented as MLEval tool {--} you can find: (1) anomalies in test sets, (2) issues in preprocessing, (3) problems in the ML model itself. It can give you an insight into what can be improved in the datasets and/or the model. The same method can be used to compare ML models or different versions of the same model. We present the tool, the theory behind it and use cases for text-based models of various types.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gralinski-etal-2019-geval">
<titleInfo>
<title>GEval: Tool for Debugging NLP Datasets and Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Graliński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Wróblewska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Stanisławek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kamil</namePart>
<namePart type="family">Grabowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Górecki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tal</namePart>
<namePart type="family">Linzen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grzegorz</namePart>
<namePart type="family">Chrupała</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">Dieuwke</namePart>
<namePart type="family">Hupkes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents a simple but general and effective method to debug the output of machine learning (ML) supervised models, including neural networks. The algorithm looks for features that lower the evaluation metric in such a way that it cannot be ascribed to chance (as measured by their p-values). Using this method – implemented as MLEval tool – you can find: (1) anomalies in test sets, (2) issues in preprocessing, (3) problems in the ML model itself. It can give you an insight into what can be improved in the datasets and/or the model. The same method can be used to compare ML models or different versions of the same model. We present the tool, the theory behind it and use cases for text-based models of various types.</abstract>
<identifier type="citekey">gralinski-etal-2019-geval</identifier>
<identifier type="doi">10.18653/v1/W19-4826</identifier>
<location>
<url>https://aclanthology.org/W19-4826</url>
</location>
<part>
<date>2019-08</date>
<extent unit="page">
<start>254</start>
<end>262</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GEval: Tool for Debugging NLP Datasets and Models
%A Graliński, Filip
%A Wróblewska, Anna
%A Stanisławek, Tomasz
%A Grabowski, Kamil
%A Górecki, Tomasz
%Y Linzen, Tal
%Y Chrupała, Grzegorz
%Y Belinkov, Yonatan
%Y Hupkes, Dieuwke
%S Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP
%D 2019
%8 August
%I Association for Computational Linguistics
%C Florence, Italy
%F gralinski-etal-2019-geval
%X This paper presents a simple but general and effective method to debug the output of machine learning (ML) supervised models, including neural networks. The algorithm looks for features that lower the evaluation metric in such a way that it cannot be ascribed to chance (as measured by their p-values). Using this method – implemented as MLEval tool – you can find: (1) anomalies in test sets, (2) issues in preprocessing, (3) problems in the ML model itself. It can give you an insight into what can be improved in the datasets and/or the model. The same method can be used to compare ML models or different versions of the same model. We present the tool, the theory behind it and use cases for text-based models of various types.
%R 10.18653/v1/W19-4826
%U https://aclanthology.org/W19-4826
%U https://doi.org/10.18653/v1/W19-4826
%P 254-262
Markdown (Informal)
[GEval: Tool for Debugging NLP Datasets and Models](https://aclanthology.org/W19-4826) (Graliński et al., BlackboxNLP 2019)
ACL
- Filip Graliński, Anna Wróblewska, Tomasz Stanisławek, Kamil Grabowski, and Tomasz Górecki. 2019. GEval: Tool for Debugging NLP Datasets and Models. In Proceedings of the 2019 ACL Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pages 254–262, Florence, Italy. Association for Computational Linguistics.