@inproceedings{cai-etal-2021-web-scale,
title = "A Web Scale Entity Extraction System",
author = "Cai, Xuanting and
Ma, Quanbin and
Liu, Jianyu and
Li, Pan and
Zeng, Qi and
Yang, Zhengkan and
Tripathi, Pushkar",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.7",
doi = "10.18653/v1/2021.findings-emnlp.7",
pages = "69--73",
abstract = "Understanding the semantic meaning of content on the web through the lens of entities and concepts has many practical advantages. However, when building large-scale entity extraction systems, practitioners are facing unique challenges involving finding the best ways to leverage the scale and variety of data available on internet platforms. We present learnings from our efforts in building an entity extraction system for multiple document types at large scale using multi-modal Transformers. We empirically demonstrate the effectiveness of multi-lingual, multi-task and cross-document type learning. We also discuss the label collection schemes that help to minimize the amount of noise in the collected data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cai-etal-2021-web-scale">
<titleInfo>
<title>A Web Scale Entity Extraction System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuanting</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quanbin</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianyu</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhengkan</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pushkar</namePart>
<namePart type="family">Tripathi</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>Findings of the Association for Computational Linguistics: EMNLP 2021</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">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Understanding the semantic meaning of content on the web through the lens of entities and concepts has many practical advantages. However, when building large-scale entity extraction systems, practitioners are facing unique challenges involving finding the best ways to leverage the scale and variety of data available on internet platforms. We present learnings from our efforts in building an entity extraction system for multiple document types at large scale using multi-modal Transformers. We empirically demonstrate the effectiveness of multi-lingual, multi-task and cross-document type learning. We also discuss the label collection schemes that help to minimize the amount of noise in the collected data.</abstract>
<identifier type="citekey">cai-etal-2021-web-scale</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.7</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.7</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>69</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Web Scale Entity Extraction System
%A Cai, Xuanting
%A Ma, Quanbin
%A Liu, Jianyu
%A Li, Pan
%A Zeng, Qi
%A Yang, Zhengkan
%A Tripathi, Pushkar
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F cai-etal-2021-web-scale
%X Understanding the semantic meaning of content on the web through the lens of entities and concepts has many practical advantages. However, when building large-scale entity extraction systems, practitioners are facing unique challenges involving finding the best ways to leverage the scale and variety of data available on internet platforms. We present learnings from our efforts in building an entity extraction system for multiple document types at large scale using multi-modal Transformers. We empirically demonstrate the effectiveness of multi-lingual, multi-task and cross-document type learning. We also discuss the label collection schemes that help to minimize the amount of noise in the collected data.
%R 10.18653/v1/2021.findings-emnlp.7
%U https://aclanthology.org/2021.findings-emnlp.7
%U https://doi.org/10.18653/v1/2021.findings-emnlp.7
%P 69-73
Markdown (Informal)
[A Web Scale Entity Extraction System](https://aclanthology.org/2021.findings-emnlp.7) (Cai et al., Findings 2021)
ACL
- Xuanting Cai, Quanbin Ma, Jianyu Liu, Pan Li, Qi Zeng, Zhengkan Yang, and Pushkar Tripathi. 2021. A Web Scale Entity Extraction System. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 69–73, Punta Cana, Dominican Republic. Association for Computational Linguistics.