@inproceedings{shen-etal-2021-sciconceptminer,
title = "{S}ci{C}oncept{M}iner: A system for large-scale scientific concept discovery",
author = "Shen, Zhihong and
Wu, Chieh-Han and
Ma, Li and
Chen, Chien-Pang and
Wang, Kuansan",
editor = "Ji, Heng and
Park, Jong C. and
Xia, Rui",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-demo.6",
doi = "10.18653/v1/2021.acl-demo.6",
pages = "48--54",
abstract = "Scientific knowledge is evolving at an unprecedented rate of speed, with new concepts constantly being introduced from millions of academic articles published every month. In this paper, we introduce a self-supervised end-to-end system, SciConceptMiner, for the automatic capture of emerging scientific concepts from both independent knowledge sources (semi-structured data) and academic publications (unstructured documents). First, we adopt a BERT-based sequence labeling model to predict candidate concept phrases with self-supervision data. Then, we incorporate rich Web content for synonym detection and concept selection via a web search API. This two-stage approach achieves highly accurate (94.7{\%}) concept identification with more than 740K scientific concepts. These concepts are deployed in the Microsoft Academic production system and are the backbone for its semantic search capability.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shen-etal-2021-sciconceptminer">
<titleInfo>
<title>SciConceptMiner: A system for large-scale scientific concept discovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhihong</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chieh-Han</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chien-Pang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuansan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jong</namePart>
<namePart type="given">C</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Scientific knowledge is evolving at an unprecedented rate of speed, with new concepts constantly being introduced from millions of academic articles published every month. In this paper, we introduce a self-supervised end-to-end system, SciConceptMiner, for the automatic capture of emerging scientific concepts from both independent knowledge sources (semi-structured data) and academic publications (unstructured documents). First, we adopt a BERT-based sequence labeling model to predict candidate concept phrases with self-supervision data. Then, we incorporate rich Web content for synonym detection and concept selection via a web search API. This two-stage approach achieves highly accurate (94.7%) concept identification with more than 740K scientific concepts. These concepts are deployed in the Microsoft Academic production system and are the backbone for its semantic search capability.</abstract>
<identifier type="citekey">shen-etal-2021-sciconceptminer</identifier>
<identifier type="doi">10.18653/v1/2021.acl-demo.6</identifier>
<location>
<url>https://aclanthology.org/2021.acl-demo.6</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>48</start>
<end>54</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SciConceptMiner: A system for large-scale scientific concept discovery
%A Shen, Zhihong
%A Wu, Chieh-Han
%A Ma, Li
%A Chen, Chien-Pang
%A Wang, Kuansan
%Y Ji, Heng
%Y Park, Jong C.
%Y Xia, Rui
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F shen-etal-2021-sciconceptminer
%X Scientific knowledge is evolving at an unprecedented rate of speed, with new concepts constantly being introduced from millions of academic articles published every month. In this paper, we introduce a self-supervised end-to-end system, SciConceptMiner, for the automatic capture of emerging scientific concepts from both independent knowledge sources (semi-structured data) and academic publications (unstructured documents). First, we adopt a BERT-based sequence labeling model to predict candidate concept phrases with self-supervision data. Then, we incorporate rich Web content for synonym detection and concept selection via a web search API. This two-stage approach achieves highly accurate (94.7%) concept identification with more than 740K scientific concepts. These concepts are deployed in the Microsoft Academic production system and are the backbone for its semantic search capability.
%R 10.18653/v1/2021.acl-demo.6
%U https://aclanthology.org/2021.acl-demo.6
%U https://doi.org/10.18653/v1/2021.acl-demo.6
%P 48-54
Markdown (Informal)
[SciConceptMiner: A system for large-scale scientific concept discovery](https://aclanthology.org/2021.acl-demo.6) (Shen et al., ACL-IJCNLP 2021)
ACL
- Zhihong Shen, Chieh-Han Wu, Li Ma, Chien-Pang Chen, and Kuansan Wang. 2021. SciConceptMiner: A system for large-scale scientific concept discovery. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations, pages 48–54, Online. Association for Computational Linguistics.