@inproceedings{zhou-etal-2023-selective,
title = "Selective Labeling: How to Radically Lower Data-Labeling Costs for Document Extraction Models",
author = "Zhou, Yichao and
Wendt, James Bradley and
Potti, Navneet and
Xie, Jing and
Tata, Sandeep",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.233",
doi = "10.18653/v1/2023.emnlp-main.233",
pages = "3847--3860",
abstract = "Building automatic extraction models for visually rich documents like invoices, receipts, bills, tax forms, etc. has received significant attention lately. A key bottleneck in developing extraction models for new document types is the cost of acquiring the several thousand high-quality labeled documents that are needed to train a model with acceptable accuracy. In this paper, we propose selective labeling as a solution to this problem. The key insight is to simplify the labeling task to provide {``}yes/no{''} labels for candidate extractions predicted by a model trained on partially labeled documents. We combine this with a custom active learning strategy to find the predictions that the model is most uncertain about. We show through experiments on document types drawn from 3 different domains that selective labeling can reduce the cost of acquiring labeled data by 10$\times$ with a negligible loss in accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2023-selective">
<titleInfo>
<title>Selective Labeling: How to Radically Lower Data-Labeling Costs for Document Extraction Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="given">Bradley</namePart>
<namePart type="family">Wendt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Navneet</namePart>
<namePart type="family">Potti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Tata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Building automatic extraction models for visually rich documents like invoices, receipts, bills, tax forms, etc. has received significant attention lately. A key bottleneck in developing extraction models for new document types is the cost of acquiring the several thousand high-quality labeled documents that are needed to train a model with acceptable accuracy. In this paper, we propose selective labeling as a solution to this problem. The key insight is to simplify the labeling task to provide “yes/no” labels for candidate extractions predicted by a model trained on partially labeled documents. We combine this with a custom active learning strategy to find the predictions that the model is most uncertain about. We show through experiments on document types drawn from 3 different domains that selective labeling can reduce the cost of acquiring labeled data by 10\times with a negligible loss in accuracy.</abstract>
<identifier type="citekey">zhou-etal-2023-selective</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.233</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.233</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>3847</start>
<end>3860</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Selective Labeling: How to Radically Lower Data-Labeling Costs for Document Extraction Models
%A Zhou, Yichao
%A Wendt, James Bradley
%A Potti, Navneet
%A Xie, Jing
%A Tata, Sandeep
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhou-etal-2023-selective
%X Building automatic extraction models for visually rich documents like invoices, receipts, bills, tax forms, etc. has received significant attention lately. A key bottleneck in developing extraction models for new document types is the cost of acquiring the several thousand high-quality labeled documents that are needed to train a model with acceptable accuracy. In this paper, we propose selective labeling as a solution to this problem. The key insight is to simplify the labeling task to provide “yes/no” labels for candidate extractions predicted by a model trained on partially labeled documents. We combine this with a custom active learning strategy to find the predictions that the model is most uncertain about. We show through experiments on document types drawn from 3 different domains that selective labeling can reduce the cost of acquiring labeled data by 10\times with a negligible loss in accuracy.
%R 10.18653/v1/2023.emnlp-main.233
%U https://aclanthology.org/2023.emnlp-main.233
%U https://doi.org/10.18653/v1/2023.emnlp-main.233
%P 3847-3860
Markdown (Informal)
[Selective Labeling: How to Radically Lower Data-Labeling Costs for Document Extraction Models](https://aclanthology.org/2023.emnlp-main.233) (Zhou et al., EMNLP 2023)
ACL