@inproceedings{geiger-etal-2019-posing,
title = "Posing Fair Generalization Tasks for Natural Language Inference",
author = "Geiger, Atticus and
Cases, Ignacio and
Karttunen, Lauri and
Potts, Christopher",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1456",
doi = "10.18653/v1/D19-1456",
pages = "4485--4495",
abstract = "Deep learning models for semantics are generally evaluated using naturalistic corpora. Adversarial testing methods, in which models are evaluated on new examples with known semantic properties, have begun to reveal that good performance at these naturalistic tasks can hide serious shortcomings. However, we should insist that these evaluations be fair {--} that the models are given data sufficient to support the requisite kinds of generalization. In this paper, we define and motivate a formal notion of fairness in this sense. We then apply these ideas to natural language inference by constructing very challenging but provably fair artificial datasets and showing that standard neural models fail to generalize in the required ways; only task-specific models that jointly compose the premise and hypothesis are able to achieve high performance, and even these models do not solve the task perfectly.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="geiger-etal-2019-posing">
<titleInfo>
<title>Posing Fair Generalization Tasks for Natural Language Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atticus</namePart>
<namePart type="family">Geiger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ignacio</namePart>
<namePart type="family">Cases</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lauri</namePart>
<namePart type="family">Karttunen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Potts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Deep learning models for semantics are generally evaluated using naturalistic corpora. Adversarial testing methods, in which models are evaluated on new examples with known semantic properties, have begun to reveal that good performance at these naturalistic tasks can hide serious shortcomings. However, we should insist that these evaluations be fair – that the models are given data sufficient to support the requisite kinds of generalization. In this paper, we define and motivate a formal notion of fairness in this sense. We then apply these ideas to natural language inference by constructing very challenging but provably fair artificial datasets and showing that standard neural models fail to generalize in the required ways; only task-specific models that jointly compose the premise and hypothesis are able to achieve high performance, and even these models do not solve the task perfectly.</abstract>
<identifier type="citekey">geiger-etal-2019-posing</identifier>
<identifier type="doi">10.18653/v1/D19-1456</identifier>
<location>
<url>https://aclanthology.org/D19-1456</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>4485</start>
<end>4495</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Posing Fair Generalization Tasks for Natural Language Inference
%A Geiger, Atticus
%A Cases, Ignacio
%A Karttunen, Lauri
%A Potts, Christopher
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F geiger-etal-2019-posing
%X Deep learning models for semantics are generally evaluated using naturalistic corpora. Adversarial testing methods, in which models are evaluated on new examples with known semantic properties, have begun to reveal that good performance at these naturalistic tasks can hide serious shortcomings. However, we should insist that these evaluations be fair – that the models are given data sufficient to support the requisite kinds of generalization. In this paper, we define and motivate a formal notion of fairness in this sense. We then apply these ideas to natural language inference by constructing very challenging but provably fair artificial datasets and showing that standard neural models fail to generalize in the required ways; only task-specific models that jointly compose the premise and hypothesis are able to achieve high performance, and even these models do not solve the task perfectly.
%R 10.18653/v1/D19-1456
%U https://aclanthology.org/D19-1456
%U https://doi.org/10.18653/v1/D19-1456
%P 4485-4495
Markdown (Informal)
[Posing Fair Generalization Tasks for Natural Language Inference](https://aclanthology.org/D19-1456) (Geiger et al., EMNLP-IJCNLP 2019)
ACL
- Atticus Geiger, Ignacio Cases, Lauri Karttunen, and Christopher Potts. 2019. Posing Fair Generalization Tasks for Natural Language Inference. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 4485–4495, Hong Kong, China. Association for Computational Linguistics.