@inproceedings{liu-etal-2020-gender,
title = "Does Gender Matter? Towards Fairness in Dialogue Systems",
author = "Liu, Haochen and
Dacon, Jamell and
Fan, Wenqi and
Liu, Hui and
Liu, Zitao and
Tang, Jiliang",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.390",
doi = "10.18653/v1/2020.coling-main.390",
pages = "4403--4416",
abstract = "Recently there are increasing concerns about the fairness of Artificial Intelligence (AI) in real-world applications such as computer vision and recommendations. For example, recognition algorithms in computer vision are unfair to black people such as poorly detecting their faces and inappropriately identifying them as {``}gorillas{''}. As one crucial application of AI, dialogue systems have been extensively applied in our society. They are usually built with real human conversational data; thus they could inherit some fairness issues which are held in the real world. However, the fairness of dialogue systems has not been well investigated. In this paper, we perform a pioneering study about the fairness issues in dialogue systems. In particular, we construct a benchmark dataset and propose quantitative measures to understand fairness in dialogue models. Our studies demonstrate that popular dialogue models show significant prejudice towards different genders and races. Besides, to mitigate the bias in dialogue systems, we propose two simple but effective debiasing methods. Experiments show that our methods can reduce the bias in dialogue systems significantly. The dataset and the implementation are released to foster fairness research in dialogue systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2020-gender">
<titleInfo>
<title>Does Gender Matter? Towards Fairness in Dialogue Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haochen</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jamell</namePart>
<namePart type="family">Dacon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqi</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zitao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiliang</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recently there are increasing concerns about the fairness of Artificial Intelligence (AI) in real-world applications such as computer vision and recommendations. For example, recognition algorithms in computer vision are unfair to black people such as poorly detecting their faces and inappropriately identifying them as “gorillas”. As one crucial application of AI, dialogue systems have been extensively applied in our society. They are usually built with real human conversational data; thus they could inherit some fairness issues which are held in the real world. However, the fairness of dialogue systems has not been well investigated. In this paper, we perform a pioneering study about the fairness issues in dialogue systems. In particular, we construct a benchmark dataset and propose quantitative measures to understand fairness in dialogue models. Our studies demonstrate that popular dialogue models show significant prejudice towards different genders and races. Besides, to mitigate the bias in dialogue systems, we propose two simple but effective debiasing methods. Experiments show that our methods can reduce the bias in dialogue systems significantly. The dataset and the implementation are released to foster fairness research in dialogue systems.</abstract>
<identifier type="citekey">liu-etal-2020-gender</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.390</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.390</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>4403</start>
<end>4416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Does Gender Matter? Towards Fairness in Dialogue Systems
%A Liu, Haochen
%A Dacon, Jamell
%A Fan, Wenqi
%A Liu, Hui
%A Liu, Zitao
%A Tang, Jiliang
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 dec
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F liu-etal-2020-gender
%X Recently there are increasing concerns about the fairness of Artificial Intelligence (AI) in real-world applications such as computer vision and recommendations. For example, recognition algorithms in computer vision are unfair to black people such as poorly detecting their faces and inappropriately identifying them as “gorillas”. As one crucial application of AI, dialogue systems have been extensively applied in our society. They are usually built with real human conversational data; thus they could inherit some fairness issues which are held in the real world. However, the fairness of dialogue systems has not been well investigated. In this paper, we perform a pioneering study about the fairness issues in dialogue systems. In particular, we construct a benchmark dataset and propose quantitative measures to understand fairness in dialogue models. Our studies demonstrate that popular dialogue models show significant prejudice towards different genders and races. Besides, to mitigate the bias in dialogue systems, we propose two simple but effective debiasing methods. Experiments show that our methods can reduce the bias in dialogue systems significantly. The dataset and the implementation are released to foster fairness research in dialogue systems.
%R 10.18653/v1/2020.coling-main.390
%U https://aclanthology.org/2020.coling-main.390
%U https://doi.org/10.18653/v1/2020.coling-main.390
%P 4403-4416
Markdown (Informal)
[Does Gender Matter? Towards Fairness in Dialogue Systems](https://aclanthology.org/2020.coling-main.390) (Liu et al., COLING 2020)
ACL
- Haochen Liu, Jamell Dacon, Wenqi Fan, Hui Liu, Zitao Liu, and Jiliang Tang. 2020. Does Gender Matter? Towards Fairness in Dialogue Systems. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4403–4416, Barcelona, Spain (Online). International Committee on Computational Linguistics.