@inproceedings{abhishek-etal-2022-spear,
title = "{SPEAR} : Semi-supervised Data Programming in Python",
author = "Abhishek, Guttu and
Ingole, Harshad and
Laturia, Parth and
Dorna, Vineeth and
Maheshwari, Ayush and
Ramakrishnan, Ganesh and
Iyer, Rishabh",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.12",
doi = "10.18653/v1/2022.emnlp-demos.12",
pages = "121--127",
abstract = "We present SPEAR, an open-source python library for data programming with semi supervision. The package implements several recent data programming approaches including facility to programmatically label and build training data. SPEAR facilitates weak supervision in the form of heuristics (or rules) and association of noisy labels to the training dataset. These noisy labels are aggregated to assign labels to the unlabeled data for downstream tasks. We have implemented several label aggregation approaches that aggregate the noisy labels and then train using the noisily labeled set in a cascaded manner. Our implementation also includes other approaches that jointly aggregate and train the model for text classification tasks. Thus, in our python package, we integrate several cascade and joint data-programming approaches while also providing the facility of data programming by letting the user define labeling functions or rules. The code and tutorial notebooks are available at \url{https://github.com/decile-team/spear}. Further, extensive documentation can be found at \url{https://spear-decile.readthedocs.io/}. Video tutorials demonstrating the usage of our package are available \url{https://youtube.com/playlist?list=PLW8agt_HvkVnOJoJAqBpaerFb-z-ZlqlP}. We also present some real-world use cases of SPEAR.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abhishek-etal-2022-spear">
<titleInfo>
<title>SPEAR : Semi-supervised Data Programming in Python</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guttu</namePart>
<namePart type="family">Abhishek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harshad</namePart>
<namePart type="family">Ingole</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parth</namePart>
<namePart type="family">Laturia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vineeth</namePart>
<namePart type="family">Dorna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayush</namePart>
<namePart type="family">Maheshwari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ganesh</namePart>
<namePart type="family">Ramakrishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rishabh</namePart>
<namePart type="family">Iyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present SPEAR, an open-source python library for data programming with semi supervision. The package implements several recent data programming approaches including facility to programmatically label and build training data. SPEAR facilitates weak supervision in the form of heuristics (or rules) and association of noisy labels to the training dataset. These noisy labels are aggregated to assign labels to the unlabeled data for downstream tasks. We have implemented several label aggregation approaches that aggregate the noisy labels and then train using the noisily labeled set in a cascaded manner. Our implementation also includes other approaches that jointly aggregate and train the model for text classification tasks. Thus, in our python package, we integrate several cascade and joint data-programming approaches while also providing the facility of data programming by letting the user define labeling functions or rules. The code and tutorial notebooks are available at https://github.com/decile-team/spear. Further, extensive documentation can be found at https://spear-decile.readthedocs.io/. Video tutorials demonstrating the usage of our package are available https://youtube.com/playlist?list=PLW8agt_HvkVnOJoJAqBpaerFb-z-ZlqlP. We also present some real-world use cases of SPEAR.</abstract>
<identifier type="citekey">abhishek-etal-2022-spear</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.12</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.12</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>121</start>
<end>127</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPEAR : Semi-supervised Data Programming in Python
%A Abhishek, Guttu
%A Ingole, Harshad
%A Laturia, Parth
%A Dorna, Vineeth
%A Maheshwari, Ayush
%A Ramakrishnan, Ganesh
%A Iyer, Rishabh
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F abhishek-etal-2022-spear
%X We present SPEAR, an open-source python library for data programming with semi supervision. The package implements several recent data programming approaches including facility to programmatically label and build training data. SPEAR facilitates weak supervision in the form of heuristics (or rules) and association of noisy labels to the training dataset. These noisy labels are aggregated to assign labels to the unlabeled data for downstream tasks. We have implemented several label aggregation approaches that aggregate the noisy labels and then train using the noisily labeled set in a cascaded manner. Our implementation also includes other approaches that jointly aggregate and train the model for text classification tasks. Thus, in our python package, we integrate several cascade and joint data-programming approaches while also providing the facility of data programming by letting the user define labeling functions or rules. The code and tutorial notebooks are available at https://github.com/decile-team/spear. Further, extensive documentation can be found at https://spear-decile.readthedocs.io/. Video tutorials demonstrating the usage of our package are available https://youtube.com/playlist?list=PLW8agt_HvkVnOJoJAqBpaerFb-z-ZlqlP. We also present some real-world use cases of SPEAR.
%R 10.18653/v1/2022.emnlp-demos.12
%U https://aclanthology.org/2022.emnlp-demos.12
%U https://doi.org/10.18653/v1/2022.emnlp-demos.12
%P 121-127
Markdown (Informal)
[SPEAR : Semi-supervised Data Programming in Python](https://aclanthology.org/2022.emnlp-demos.12) (Abhishek et al., EMNLP 2022)
ACL
- Guttu Abhishek, Harshad Ingole, Parth Laturia, Vineeth Dorna, Ayush Maheshwari, Ganesh Ramakrishnan, and Rishabh Iyer. 2022. SPEAR : Semi-supervised Data Programming in Python. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 121–127, Abu Dhabi, UAE. Association for Computational Linguistics.