@inproceedings{r-menon-etal-2023-coaug,
title = "{C}o{A}ug: Combining Augmentation of Labels and Labelling Rules",
author = "R. Menon, Rakesh and
Wang, Bingqing and
Araki, Jun and
Zhou, Zhengyu and
Feng, Zhe and
Ren, Liu",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.577",
doi = "10.18653/v1/2023.findings-acl.577",
pages = "9062--9071",
abstract = "Collecting labeled data for Named Entity Recognition (NER) tasks is challenging due to the high cost of manual annotations. Instead, researchers have proposed few-shot self-training and rule-augmentation techniques to minimize the reliance on large datasets. However, inductive biases and restricted logical language lexicon, respectively, can limit the ability of these models to perform well. In this work, we propose CoAug, a co-augmentation framework that allows us to improve few-shot models and rule-augmentation models by bootstrapping predictions from each model. By leveraging rules and neural model predictions to train our models, we complement the benefits of each and achieve the best of both worlds. In our experiments, we show that our best CoAug model can outperform strong weak-supervision-based NER models at least by 6.5 F1 points.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="r-menon-etal-2023-coaug">
<titleInfo>
<title>CoAug: Combining Augmentation of Labels and Labelling Rules</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rakesh</namePart>
<namePart type="family">R. Menon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bingqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Araki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengyu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhe</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Collecting labeled data for Named Entity Recognition (NER) tasks is challenging due to the high cost of manual annotations. Instead, researchers have proposed few-shot self-training and rule-augmentation techniques to minimize the reliance on large datasets. However, inductive biases and restricted logical language lexicon, respectively, can limit the ability of these models to perform well. In this work, we propose CoAug, a co-augmentation framework that allows us to improve few-shot models and rule-augmentation models by bootstrapping predictions from each model. By leveraging rules and neural model predictions to train our models, we complement the benefits of each and achieve the best of both worlds. In our experiments, we show that our best CoAug model can outperform strong weak-supervision-based NER models at least by 6.5 F1 points.</abstract>
<identifier type="citekey">r-menon-etal-2023-coaug</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.577</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.577</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>9062</start>
<end>9071</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CoAug: Combining Augmentation of Labels and Labelling Rules
%A R. Menon, Rakesh
%A Wang, Bingqing
%A Araki, Jun
%A Zhou, Zhengyu
%A Feng, Zhe
%A Ren, Liu
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F r-menon-etal-2023-coaug
%X Collecting labeled data for Named Entity Recognition (NER) tasks is challenging due to the high cost of manual annotations. Instead, researchers have proposed few-shot self-training and rule-augmentation techniques to minimize the reliance on large datasets. However, inductive biases and restricted logical language lexicon, respectively, can limit the ability of these models to perform well. In this work, we propose CoAug, a co-augmentation framework that allows us to improve few-shot models and rule-augmentation models by bootstrapping predictions from each model. By leveraging rules and neural model predictions to train our models, we complement the benefits of each and achieve the best of both worlds. In our experiments, we show that our best CoAug model can outperform strong weak-supervision-based NER models at least by 6.5 F1 points.
%R 10.18653/v1/2023.findings-acl.577
%U https://aclanthology.org/2023.findings-acl.577
%U https://doi.org/10.18653/v1/2023.findings-acl.577
%P 9062-9071
Markdown (Informal)
[CoAug: Combining Augmentation of Labels and Labelling Rules](https://aclanthology.org/2023.findings-acl.577) (R. Menon et al., Findings 2023)
ACL
- Rakesh R. Menon, Bingqing Wang, Jun Araki, Zhengyu Zhou, Zhe Feng, and Liu Ren. 2023. CoAug: Combining Augmentation of Labels and Labelling Rules. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9062–9071, Toronto, Canada. Association for Computational Linguistics.