@inproceedings{mekala-etal-2021-coarse2fine,
title = "{C}oarse2{F}ine: Fine-grained Text Classification on Coarsely-grained Annotated Data",
author = "Mekala, Dheeraj and
Gangal, Varun and
Shang, Jingbo",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.46",
doi = "10.18653/v1/2021.emnlp-main.46",
pages = "583--594",
abstract = "Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we introduce a new problem called coarse-to-fine grained classification, which aims to perform fine-grained classification on coarsely annotated data. Instead of asking for new fine-grained human annotations, we opt to leverage label surface names as the only human guidance and weave in rich pre-trained generative language models into the iterative weak supervision strategy. Specifically, we first propose a label-conditioned fine-tuning formulation to attune these generators for our task. Furthermore, we devise a regularization objective based on the coarse-fine label constraints derived from our problem setting, giving us even further improvements over the prior formulation. Our framework uses the fine-tuned generative models to sample pseudo-training data for training the classifier, and bootstraps on real unlabeled data for model refinement. Extensive experiments and case studies on two real-world datasets demonstrate superior performance over SOTA zero-shot classification baselines.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mekala-etal-2021-coarse2fine">
<titleInfo>
<title>Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dheeraj</namePart>
<namePart type="family">Mekala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Varun</namePart>
<namePart type="family">Gangal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingbo</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we introduce a new problem called coarse-to-fine grained classification, which aims to perform fine-grained classification on coarsely annotated data. Instead of asking for new fine-grained human annotations, we opt to leverage label surface names as the only human guidance and weave in rich pre-trained generative language models into the iterative weak supervision strategy. Specifically, we first propose a label-conditioned fine-tuning formulation to attune these generators for our task. Furthermore, we devise a regularization objective based on the coarse-fine label constraints derived from our problem setting, giving us even further improvements over the prior formulation. Our framework uses the fine-tuned generative models to sample pseudo-training data for training the classifier, and bootstraps on real unlabeled data for model refinement. Extensive experiments and case studies on two real-world datasets demonstrate superior performance over SOTA zero-shot classification baselines.</abstract>
<identifier type="citekey">mekala-etal-2021-coarse2fine</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.46</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.46</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>583</start>
<end>594</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data
%A Mekala, Dheeraj
%A Gangal, Varun
%A Shang, Jingbo
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F mekala-etal-2021-coarse2fine
%X Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases. To accommodate such requirements, we introduce a new problem called coarse-to-fine grained classification, which aims to perform fine-grained classification on coarsely annotated data. Instead of asking for new fine-grained human annotations, we opt to leverage label surface names as the only human guidance and weave in rich pre-trained generative language models into the iterative weak supervision strategy. Specifically, we first propose a label-conditioned fine-tuning formulation to attune these generators for our task. Furthermore, we devise a regularization objective based on the coarse-fine label constraints derived from our problem setting, giving us even further improvements over the prior formulation. Our framework uses the fine-tuned generative models to sample pseudo-training data for training the classifier, and bootstraps on real unlabeled data for model refinement. Extensive experiments and case studies on two real-world datasets demonstrate superior performance over SOTA zero-shot classification baselines.
%R 10.18653/v1/2021.emnlp-main.46
%U https://aclanthology.org/2021.emnlp-main.46
%U https://doi.org/10.18653/v1/2021.emnlp-main.46
%P 583-594
Markdown (Informal)
[Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data](https://aclanthology.org/2021.emnlp-main.46) (Mekala et al., EMNLP 2021)
ACL