@inproceedings{sun-etal-2023-dialect,
title = "Dialect-robust Evaluation of Generated Text",
author = "Sun, Jiao and
Sellam, Thibault and
Clark, Elizabeth and
Vu, Tu and
Dozat, Timothy and
Garrette, Dan and
Siddhant, Aditya and
Eisenstein, Jacob and
Gehrmann, Sebastian",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.331",
doi = "10.18653/v1/2023.acl-long.331",
pages = "6010--6028",
abstract = "Text generation metrics that are not robust to dialect variation make it impossible to tell how well systems perform for many groups of users, and can even penalize systems for producing text in lower-resource dialects. In this paper, we introduce a suite of methods to assess whether metrics are dialect robust. These methods show that state-of-the-art metrics are not dialect robust: they often prioritize dialect similarity over semantics, preferring outputs that are semantically incorrect over outputs that match the semantics of the reference but contain dialect differences. As a step towards dialect-robust metrics for text generation, we propose NANO, which introduces regional and language information to the metric{'}s pretraining. NANO significantly improves dialect robustness while preserving the correlation between automated metrics and human ratings. It also enables a more ambitious approach to evaluation, dialect awareness, in which system outputs are scored by both semantic match to the reference and appropriateness in any specified dialect.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2023-dialect">
<titleInfo>
<title>Dialect-robust Evaluation of Generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiao</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thibault</namePart>
<namePart type="family">Sellam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Clark</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tu</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Dozat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Garrette</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Siddhant</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Eisenstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Gehrmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Text generation metrics that are not robust to dialect variation make it impossible to tell how well systems perform for many groups of users, and can even penalize systems for producing text in lower-resource dialects. In this paper, we introduce a suite of methods to assess whether metrics are dialect robust. These methods show that state-of-the-art metrics are not dialect robust: they often prioritize dialect similarity over semantics, preferring outputs that are semantically incorrect over outputs that match the semantics of the reference but contain dialect differences. As a step towards dialect-robust metrics for text generation, we propose NANO, which introduces regional and language information to the metric’s pretraining. NANO significantly improves dialect robustness while preserving the correlation between automated metrics and human ratings. It also enables a more ambitious approach to evaluation, dialect awareness, in which system outputs are scored by both semantic match to the reference and appropriateness in any specified dialect.</abstract>
<identifier type="citekey">sun-etal-2023-dialect</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.331</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.331</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6010</start>
<end>6028</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dialect-robust Evaluation of Generated Text
%A Sun, Jiao
%A Sellam, Thibault
%A Clark, Elizabeth
%A Vu, Tu
%A Dozat, Timothy
%A Garrette, Dan
%A Siddhant, Aditya
%A Eisenstein, Jacob
%A Gehrmann, Sebastian
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F sun-etal-2023-dialect
%X Text generation metrics that are not robust to dialect variation make it impossible to tell how well systems perform for many groups of users, and can even penalize systems for producing text in lower-resource dialects. In this paper, we introduce a suite of methods to assess whether metrics are dialect robust. These methods show that state-of-the-art metrics are not dialect robust: they often prioritize dialect similarity over semantics, preferring outputs that are semantically incorrect over outputs that match the semantics of the reference but contain dialect differences. As a step towards dialect-robust metrics for text generation, we propose NANO, which introduces regional and language information to the metric’s pretraining. NANO significantly improves dialect robustness while preserving the correlation between automated metrics and human ratings. It also enables a more ambitious approach to evaluation, dialect awareness, in which system outputs are scored by both semantic match to the reference and appropriateness in any specified dialect.
%R 10.18653/v1/2023.acl-long.331
%U https://aclanthology.org/2023.acl-long.331
%U https://doi.org/10.18653/v1/2023.acl-long.331
%P 6010-6028
Markdown (Informal)
[Dialect-robust Evaluation of Generated Text](https://aclanthology.org/2023.acl-long.331) (Sun et al., ACL 2023)
ACL
- Jiao Sun, Thibault Sellam, Elizabeth Clark, Tu Vu, Timothy Dozat, Dan Garrette, Aditya Siddhant, Jacob Eisenstein, and Sebastian Gehrmann. 2023. Dialect-robust Evaluation of Generated Text. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6010–6028, Toronto, Canada. Association for Computational Linguistics.