@inproceedings{thrush-etal-2022-dynatask,
title = "Dynatask: A Framework for Creating Dynamic {AI} Benchmark Tasks",
author = "Thrush, Tristan and
Tirumala, Kushal and
Gupta, Anmol and
Bartolo, Max and
Rodriguez, Pedro and
Kane, Tariq and
Gaviria Rojas, William and
Mattson, Peter and
Williams, Adina and
Kiela, Douwe",
editor = "Basile, Valerio and
Kozareva, Zornitsa and
Stajner, Sanja",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-demo.17",
doi = "10.18653/v1/2022.acl-demo.17",
pages = "174--181",
abstract = "We introduce Dynatask: an open source system for setting up custom NLP tasks that aims to greatly lower the technical knowledge and effort required for hosting and evaluating state-of-the-art NLP models, as well as for conducting model in the loop data collection with crowdworkers. Dynatask is integrated with Dynabench, a research platform for rethinking benchmarking in AI that facilitates human and model in the loop data collection and evaluation. To create a task, users only need to write a short task configuration file from which the relevant web interfaces and model hosting infrastructure are automatically generated. The system is available at \url{https://dynabench.org/} and the full library can be found at \url{https://github.com/facebookresearch/dynabench}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thrush-etal-2022-dynatask">
<titleInfo>
<title>Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Thrush</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kushal</namePart>
<namePart type="family">Tirumala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anmol</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Max</namePart>
<namePart type="family">Bartolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pedro</namePart>
<namePart type="family">Rodriguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tariq</namePart>
<namePart type="family">Kane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Gaviria Rojas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Mattson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adina</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Douwe</namePart>
<namePart type="family">Kiela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Stajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Dynatask: an open source system for setting up custom NLP tasks that aims to greatly lower the technical knowledge and effort required for hosting and evaluating state-of-the-art NLP models, as well as for conducting model in the loop data collection with crowdworkers. Dynatask is integrated with Dynabench, a research platform for rethinking benchmarking in AI that facilitates human and model in the loop data collection and evaluation. To create a task, users only need to write a short task configuration file from which the relevant web interfaces and model hosting infrastructure are automatically generated. The system is available at https://dynabench.org/ and the full library can be found at https://github.com/facebookresearch/dynabench.</abstract>
<identifier type="citekey">thrush-etal-2022-dynatask</identifier>
<identifier type="doi">10.18653/v1/2022.acl-demo.17</identifier>
<location>
<url>https://aclanthology.org/2022.acl-demo.17</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>174</start>
<end>181</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks
%A Thrush, Tristan
%A Tirumala, Kushal
%A Gupta, Anmol
%A Bartolo, Max
%A Rodriguez, Pedro
%A Kane, Tariq
%A Gaviria Rojas, William
%A Mattson, Peter
%A Williams, Adina
%A Kiela, Douwe
%Y Basile, Valerio
%Y Kozareva, Zornitsa
%Y Stajner, Sanja
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F thrush-etal-2022-dynatask
%X We introduce Dynatask: an open source system for setting up custom NLP tasks that aims to greatly lower the technical knowledge and effort required for hosting and evaluating state-of-the-art NLP models, as well as for conducting model in the loop data collection with crowdworkers. Dynatask is integrated with Dynabench, a research platform for rethinking benchmarking in AI that facilitates human and model in the loop data collection and evaluation. To create a task, users only need to write a short task configuration file from which the relevant web interfaces and model hosting infrastructure are automatically generated. The system is available at https://dynabench.org/ and the full library can be found at https://github.com/facebookresearch/dynabench.
%R 10.18653/v1/2022.acl-demo.17
%U https://aclanthology.org/2022.acl-demo.17
%U https://doi.org/10.18653/v1/2022.acl-demo.17
%P 174-181
Markdown (Informal)
[Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks](https://aclanthology.org/2022.acl-demo.17) (Thrush et al., ACL 2022)
ACL
- Tristan Thrush, Kushal Tirumala, Anmol Gupta, Max Bartolo, Pedro Rodriguez, Tariq Kane, William Gaviria Rojas, Peter Mattson, Adina Williams, and Douwe Kiela. 2022. Dynatask: A Framework for Creating Dynamic AI Benchmark Tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations, pages 174–181, Dublin, Ireland. Association for Computational Linguistics.