@inproceedings{zalmout-li-2022-prototype,
title = "Prototype-Representations for Training Data Filtering in Weakly-Supervised Information Extraction",
author = "Zalmout, Nasser and
Li, Xian",
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.47",
doi = "10.18653/v1/2022.emnlp-industry.47",
pages = "467--474",
abstract = "The availability of high quality training data is still a bottleneck for the practical utilization of information extraction models, despite the breakthroughs in zero and few-shot learning techniques. This is further exacerbated for industry applications, where new tasks, domains, and specific use cases keep arising, which makes it impractical to depend on manually annotated data. Therefore, weak and distant supervision emerged as popular approaches to bootstrap training, utilizing labeling functions to guide the annotation process. Weakly-supervised annotation of training data is fast and efficient, however, it results in many irrelevant and out-of-context matches. This is a challenging problem that can degrade the performance in downstream models, or require a manual data cleaning step that can incur significant overhead. In this paper we present a prototype-based filtering approach, that can be utilized to denoise weakly supervised training data. The system is very simple, unsupervised, scalable, and requires little manual intervention, yet results in significant precision gains. We apply the technique in the task of attribute value extraction in e-commerce websites, and achieve up to 9{\%} gain in precision for the downstream models, with a minimal drop in recall.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zalmout-li-2022-prototype">
<titleInfo>
<title>Prototype-Representations for Training Data Filtering in Weakly-Supervised Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nasser</namePart>
<namePart type="family">Zalmout</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xian</namePart>
<namePart type="family">Li</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: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</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>The availability of high quality training data is still a bottleneck for the practical utilization of information extraction models, despite the breakthroughs in zero and few-shot learning techniques. This is further exacerbated for industry applications, where new tasks, domains, and specific use cases keep arising, which makes it impractical to depend on manually annotated data. Therefore, weak and distant supervision emerged as popular approaches to bootstrap training, utilizing labeling functions to guide the annotation process. Weakly-supervised annotation of training data is fast and efficient, however, it results in many irrelevant and out-of-context matches. This is a challenging problem that can degrade the performance in downstream models, or require a manual data cleaning step that can incur significant overhead. In this paper we present a prototype-based filtering approach, that can be utilized to denoise weakly supervised training data. The system is very simple, unsupervised, scalable, and requires little manual intervention, yet results in significant precision gains. We apply the technique in the task of attribute value extraction in e-commerce websites, and achieve up to 9% gain in precision for the downstream models, with a minimal drop in recall.</abstract>
<identifier type="citekey">zalmout-li-2022-prototype</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.47</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.47</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>467</start>
<end>474</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prototype-Representations for Training Data Filtering in Weakly-Supervised Information Extraction
%A Zalmout, Nasser
%A Li, Xian
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F zalmout-li-2022-prototype
%X The availability of high quality training data is still a bottleneck for the practical utilization of information extraction models, despite the breakthroughs in zero and few-shot learning techniques. This is further exacerbated for industry applications, where new tasks, domains, and specific use cases keep arising, which makes it impractical to depend on manually annotated data. Therefore, weak and distant supervision emerged as popular approaches to bootstrap training, utilizing labeling functions to guide the annotation process. Weakly-supervised annotation of training data is fast and efficient, however, it results in many irrelevant and out-of-context matches. This is a challenging problem that can degrade the performance in downstream models, or require a manual data cleaning step that can incur significant overhead. In this paper we present a prototype-based filtering approach, that can be utilized to denoise weakly supervised training data. The system is very simple, unsupervised, scalable, and requires little manual intervention, yet results in significant precision gains. We apply the technique in the task of attribute value extraction in e-commerce websites, and achieve up to 9% gain in precision for the downstream models, with a minimal drop in recall.
%R 10.18653/v1/2022.emnlp-industry.47
%U https://aclanthology.org/2022.emnlp-industry.47
%U https://doi.org/10.18653/v1/2022.emnlp-industry.47
%P 467-474
Markdown (Informal)
[Prototype-Representations for Training Data Filtering in Weakly-Supervised Information Extraction](https://aclanthology.org/2022.emnlp-industry.47) (Zalmout & Li, EMNLP 2022)
ACL