@inproceedings{heineman-etal-2023-thresh,
title = "Thresh: A Unified, Customizable and Deployable Platform for Fine-Grained Text Evaluation",
author = "Heineman, David and
Dou, Yao and
Xu, Wei",
editor = "Feng, Yansong and
Lefever, Els",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-demo.30/",
doi = "10.18653/v1/2023.emnlp-demo.30",
pages = "336--345",
abstract = "Fine-grained, span-level human evaluation has emerged as a reliable and robust method for evaluating text generation tasks such as summarization, simplification, machine translation and news generation, and the derived annotations have been useful for training automatic metrics and improving language models. However, existing annotation tools implemented for these evaluation frameworks lack the adaptability to be extended to different domains or languages, or modify annotation settings according to user needs; and, the absence of a unified annotated data format inhibits the research in multi-task learning. In this paper, we introduce Thresh, a unified, customizable and deployable platform for fine-grained evaluation. With a single YAML configuration file, users can build and test an annotation interface for any framework within minutes {--} all in one web browser window. To facilitate collaboration and sharing, Thresh provides a community hub that hosts a collection of fine-grained frameworks and corresponding annotations made and collected by the community, covering a wide range of NLP tasks. For deployment, Thresh offers multiple options for any scale of annotation projects from small manual inspections to large crowdsourcing ones. Additionally, we introduce a Python library to streamline the entire process from typology design and deployment to annotation processing. Thresh is publicly accessible at https://thresh.tools."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="heineman-etal-2023-thresh">
<titleInfo>
<title>Thresh: A Unified, Customizable and Deployable Platform for Fine-Grained Text Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Heineman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Dou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yansong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Els</namePart>
<namePart type="family">Lefever</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fine-grained, span-level human evaluation has emerged as a reliable and robust method for evaluating text generation tasks such as summarization, simplification, machine translation and news generation, and the derived annotations have been useful for training automatic metrics and improving language models. However, existing annotation tools implemented for these evaluation frameworks lack the adaptability to be extended to different domains or languages, or modify annotation settings according to user needs; and, the absence of a unified annotated data format inhibits the research in multi-task learning. In this paper, we introduce Thresh, a unified, customizable and deployable platform for fine-grained evaluation. With a single YAML configuration file, users can build and test an annotation interface for any framework within minutes – all in one web browser window. To facilitate collaboration and sharing, Thresh provides a community hub that hosts a collection of fine-grained frameworks and corresponding annotations made and collected by the community, covering a wide range of NLP tasks. For deployment, Thresh offers multiple options for any scale of annotation projects from small manual inspections to large crowdsourcing ones. Additionally, we introduce a Python library to streamline the entire process from typology design and deployment to annotation processing. Thresh is publicly accessible at https://thresh.tools.</abstract>
<identifier type="citekey">heineman-etal-2023-thresh</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-demo.30</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-demo.30/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>336</start>
<end>345</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thresh: A Unified, Customizable and Deployable Platform for Fine-Grained Text Evaluation
%A Heineman, David
%A Dou, Yao
%A Xu, Wei
%Y Feng, Yansong
%Y Lefever, Els
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F heineman-etal-2023-thresh
%X Fine-grained, span-level human evaluation has emerged as a reliable and robust method for evaluating text generation tasks such as summarization, simplification, machine translation and news generation, and the derived annotations have been useful for training automatic metrics and improving language models. However, existing annotation tools implemented for these evaluation frameworks lack the adaptability to be extended to different domains or languages, or modify annotation settings according to user needs; and, the absence of a unified annotated data format inhibits the research in multi-task learning. In this paper, we introduce Thresh, a unified, customizable and deployable platform for fine-grained evaluation. With a single YAML configuration file, users can build and test an annotation interface for any framework within minutes – all in one web browser window. To facilitate collaboration and sharing, Thresh provides a community hub that hosts a collection of fine-grained frameworks and corresponding annotations made and collected by the community, covering a wide range of NLP tasks. For deployment, Thresh offers multiple options for any scale of annotation projects from small manual inspections to large crowdsourcing ones. Additionally, we introduce a Python library to streamline the entire process from typology design and deployment to annotation processing. Thresh is publicly accessible at https://thresh.tools.
%R 10.18653/v1/2023.emnlp-demo.30
%U https://aclanthology.org/2023.emnlp-demo.30/
%U https://doi.org/10.18653/v1/2023.emnlp-demo.30
%P 336-345
Markdown (Informal)
[Thresh: A Unified, Customizable and Deployable Platform for Fine-Grained Text Evaluation](https://aclanthology.org/2023.emnlp-demo.30/) (Heineman et al., EMNLP 2023)
ACL