@inproceedings{selvaraj-etal-2022-openhands,
title = "{O}pen{H}ands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages",
author = "Selvaraj, Prem and
Nc, Gokul and
Kumar, Pratyush and
Khapra, Mitesh",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.150",
doi = "10.18653/v1/2022.acl-long.150",
pages = "2114--2133",
abstract = "AI technologies for Natural Languages have made tremendous progress recently. However, commensurate progress has not been made on Sign Languages, in particular, in recognizing signs as individual words or as complete sentences. We introduce OpenHands, a library where we take four key ideas from the NLP community for low-resource languages and apply them to sign languages for word-level recognition. First, we propose using pose extracted through pretrained models as the standard modality of data in this work to reduce training time and enable efficient inference, and we release standardized pose datasets for different existing sign language datasets. Second, we train and release checkpoints of 4 pose-based isolated sign language recognition models across 6 languages (American, Argentinian, Chinese, Greek, Indian, and Turkish), providing baselines and ready checkpoints for deployment. Third, to address the lack of labelled data, we propose self-supervised pretraining on unlabelled data. We curate and release the largest pose-based pretraining dataset on Indian Sign Language (Indian-SL). Fourth, we compare different pretraining strategies and for the first time establish that pretraining is effective for sign language recognition by demonstrating (a) improved fine-tuning performance especially in low-resource settings, and (b) high crosslingual transfer from Indian-SL to few other sign languages. We open-source all models and datasets in OpenHands with a hope that it makes research in sign languages reproducible and more accessible.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="selvaraj-etal-2022-openhands">
<titleInfo>
<title>OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Prem</namePart>
<namePart type="family">Selvaraj</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokul</namePart>
<namePart type="family">Nc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratyush</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mitesh</namePart>
<namePart type="family">Khapra</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 (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</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>AI technologies for Natural Languages have made tremendous progress recently. However, commensurate progress has not been made on Sign Languages, in particular, in recognizing signs as individual words or as complete sentences. We introduce OpenHands, a library where we take four key ideas from the NLP community for low-resource languages and apply them to sign languages for word-level recognition. First, we propose using pose extracted through pretrained models as the standard modality of data in this work to reduce training time and enable efficient inference, and we release standardized pose datasets for different existing sign language datasets. Second, we train and release checkpoints of 4 pose-based isolated sign language recognition models across 6 languages (American, Argentinian, Chinese, Greek, Indian, and Turkish), providing baselines and ready checkpoints for deployment. Third, to address the lack of labelled data, we propose self-supervised pretraining on unlabelled data. We curate and release the largest pose-based pretraining dataset on Indian Sign Language (Indian-SL). Fourth, we compare different pretraining strategies and for the first time establish that pretraining is effective for sign language recognition by demonstrating (a) improved fine-tuning performance especially in low-resource settings, and (b) high crosslingual transfer from Indian-SL to few other sign languages. We open-source all models and datasets in OpenHands with a hope that it makes research in sign languages reproducible and more accessible.</abstract>
<identifier type="citekey">selvaraj-etal-2022-openhands</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.150</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.150</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2114</start>
<end>2133</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages
%A Selvaraj, Prem
%A Nc, Gokul
%A Kumar, Pratyush
%A Khapra, Mitesh
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F selvaraj-etal-2022-openhands
%X AI technologies for Natural Languages have made tremendous progress recently. However, commensurate progress has not been made on Sign Languages, in particular, in recognizing signs as individual words or as complete sentences. We introduce OpenHands, a library where we take four key ideas from the NLP community for low-resource languages and apply them to sign languages for word-level recognition. First, we propose using pose extracted through pretrained models as the standard modality of data in this work to reduce training time and enable efficient inference, and we release standardized pose datasets for different existing sign language datasets. Second, we train and release checkpoints of 4 pose-based isolated sign language recognition models across 6 languages (American, Argentinian, Chinese, Greek, Indian, and Turkish), providing baselines and ready checkpoints for deployment. Third, to address the lack of labelled data, we propose self-supervised pretraining on unlabelled data. We curate and release the largest pose-based pretraining dataset on Indian Sign Language (Indian-SL). Fourth, we compare different pretraining strategies and for the first time establish that pretraining is effective for sign language recognition by demonstrating (a) improved fine-tuning performance especially in low-resource settings, and (b) high crosslingual transfer from Indian-SL to few other sign languages. We open-source all models and datasets in OpenHands with a hope that it makes research in sign languages reproducible and more accessible.
%R 10.18653/v1/2022.acl-long.150
%U https://aclanthology.org/2022.acl-long.150
%U https://doi.org/10.18653/v1/2022.acl-long.150
%P 2114-2133
Markdown (Informal)
[OpenHands: Making Sign Language Recognition Accessible with Pose-based Pretrained Models across Languages](https://aclanthology.org/2022.acl-long.150) (Selvaraj et al., ACL 2022)
ACL