@inproceedings{lison-etal-2021-skweak,
title = "skweak: Weak Supervision Made Easy for {NLP}",
author = "Lison, Pierre and
Barnes, Jeremy and
Hubin, Aliaksandr",
editor = "Ji, Heng and
Park, Jong C. and
Xia, Rui",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-demo.40",
doi = "10.18653/v1/2021.acl-demo.40",
pages = "337--346",
abstract = "We present skweak, a versatile, Python-based software toolkit enabling NLP developers to apply weak supervision to a wide range of NLP tasks. Weak supervision is an emerging machine learning paradigm based on a simple idea: instead of labelling data points by hand, we use labelling functions derived from domain knowledge to automatically obtain annotations for a given dataset. The resulting labels are then aggregated with a generative model that estimates the accuracy (and possible confusions) of each labelling function. The skweak toolkit makes it easy to implement a large spectrum of labelling functions (such as heuristics, gazetteers, neural models or linguistic constraints) on text data, apply them on a corpus, and aggregate their results in a fully unsupervised fashion. skweak is especially designed to facilitate the use of weak supervision for NLP tasks such as text classification and sequence labelling. We illustrate the use of skweak for NER and sentiment analysis. skweak is released under an open-source license and is available at \url{https://github.com/NorskRegnesentral/skweak}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lison-etal-2021-skweak">
<titleInfo>
<title>skweak: Weak Supervision Made Easy for NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pierre</namePart>
<namePart type="family">Lison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aliaksandr</namePart>
<namePart type="family">Hubin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present skweak, a versatile, Python-based software toolkit enabling NLP developers to apply weak supervision to a wide range of NLP tasks. Weak supervision is an emerging machine learning paradigm based on a simple idea: instead of labelling data points by hand, we use labelling functions derived from domain knowledge to automatically obtain annotations for a given dataset. The resulting labels are then aggregated with a generative model that estimates the accuracy (and possible confusions) of each labelling function. The skweak toolkit makes it easy to implement a large spectrum of labelling functions (such as heuristics, gazetteers, neural models or linguistic constraints) on text data, apply them on a corpus, and aggregate their results in a fully unsupervised fashion. skweak is especially designed to facilitate the use of weak supervision for NLP tasks such as text classification and sequence labelling. We illustrate the use of skweak for NER and sentiment analysis. skweak is released under an open-source license and is available at https://github.com/NorskRegnesentral/skweak</abstract>
<identifier type="citekey">lison-etal-2021-skweak</identifier>
<identifier type="doi">10.18653/v1/2021.acl-demo.40</identifier>
<location>
<url>https://aclanthology.org/2021.acl-demo.40</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>337</start>
<end>346</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T skweak: Weak Supervision Made Easy for NLP
%A Lison, Pierre
%A Barnes, Jeremy
%A Hubin, Aliaksandr
%Y Ji, Heng
%Y Park, Jong C.
%Y Xia, Rui
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F lison-etal-2021-skweak
%X We present skweak, a versatile, Python-based software toolkit enabling NLP developers to apply weak supervision to a wide range of NLP tasks. Weak supervision is an emerging machine learning paradigm based on a simple idea: instead of labelling data points by hand, we use labelling functions derived from domain knowledge to automatically obtain annotations for a given dataset. The resulting labels are then aggregated with a generative model that estimates the accuracy (and possible confusions) of each labelling function. The skweak toolkit makes it easy to implement a large spectrum of labelling functions (such as heuristics, gazetteers, neural models or linguistic constraints) on text data, apply them on a corpus, and aggregate their results in a fully unsupervised fashion. skweak is especially designed to facilitate the use of weak supervision for NLP tasks such as text classification and sequence labelling. We illustrate the use of skweak for NER and sentiment analysis. skweak is released under an open-source license and is available at https://github.com/NorskRegnesentral/skweak
%R 10.18653/v1/2021.acl-demo.40
%U https://aclanthology.org/2021.acl-demo.40
%U https://doi.org/10.18653/v1/2021.acl-demo.40
%P 337-346
Markdown (Informal)
[skweak: Weak Supervision Made Easy for NLP](https://aclanthology.org/2021.acl-demo.40) (Lison et al., ACL-IJCNLP 2021)
ACL
- Pierre Lison, Jeremy Barnes, and Aliaksandr Hubin. 2021. skweak: Weak Supervision Made Easy for NLP. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations, pages 337–346, Online. Association for Computational Linguistics.