@inproceedings{jin-etal-2022-cogktr,
title = "{C}og{KTR}: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding",
author = "Jin, Zhuoran and
Men, Tianyi and
Yuan, Hongbang and
Zhou, Yuyang and
Cao, Pengfei and
Chen, Yubo and
Xue, Zhipeng and
Liu, Kang and
Zhao, Jun",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.1",
doi = "10.18653/v1/2022.emnlp-demos.1",
pages = "1--11",
abstract = "As the first step of modern natural language processing, text representation encodes discrete texts as continuous embeddings. Pre-trained language models (PLMs) have demonstrated strong ability in text representation and significantly promoted the development of natural language understanding (NLU). However, existing PLMs represent a text solely by its context, which is not enough to support knowledge-intensive NLU tasks. Knowledge is power, and fusing external knowledge explicitly into PLMs can provide knowledgeable text representations. Since previous knowledge-enhanced methods differ in many aspects, making it difficult for us to reproduce previous methods, implement new methods, and transfer between different methods. It is highly desirable to have a unified paradigm to encompass all kinds of methods in one framework. In this paper, we propose CogKTR, a knowledge-enhanced text representation toolkit for natural language understanding. According to our proposed Unified Knowledge-Enhanced Paradigm (UniKEP), CogKTR consists of four key stages, including knowledge acquisition, knowledge representation, knowledge injection, and knowledge application. CogKTR currently supports easy-to-use knowledge acquisition interfaces, multi-source knowledge embeddings, diverse knowledge-enhanced models, and various knowledge-intensive NLU tasks. Our unified, knowledgeable and modular toolkit is publicly available at GitHub, with an online system and a short instruction video.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2022-cogktr">
<titleInfo>
<title>CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhuoran</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tianyi</namePart>
<namePart type="family">Men</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongbang</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Cao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</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: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</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>As the first step of modern natural language processing, text representation encodes discrete texts as continuous embeddings. Pre-trained language models (PLMs) have demonstrated strong ability in text representation and significantly promoted the development of natural language understanding (NLU). However, existing PLMs represent a text solely by its context, which is not enough to support knowledge-intensive NLU tasks. Knowledge is power, and fusing external knowledge explicitly into PLMs can provide knowledgeable text representations. Since previous knowledge-enhanced methods differ in many aspects, making it difficult for us to reproduce previous methods, implement new methods, and transfer between different methods. It is highly desirable to have a unified paradigm to encompass all kinds of methods in one framework. In this paper, we propose CogKTR, a knowledge-enhanced text representation toolkit for natural language understanding. According to our proposed Unified Knowledge-Enhanced Paradigm (UniKEP), CogKTR consists of four key stages, including knowledge acquisition, knowledge representation, knowledge injection, and knowledge application. CogKTR currently supports easy-to-use knowledge acquisition interfaces, multi-source knowledge embeddings, diverse knowledge-enhanced models, and various knowledge-intensive NLU tasks. Our unified, knowledgeable and modular toolkit is publicly available at GitHub, with an online system and a short instruction video.</abstract>
<identifier type="citekey">jin-etal-2022-cogktr</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.1</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.1</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding
%A Jin, Zhuoran
%A Men, Tianyi
%A Yuan, Hongbang
%A Zhou, Yuyang
%A Cao, Pengfei
%A Chen, Yubo
%A Xue, Zhipeng
%A Liu, Kang
%A Zhao, Jun
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F jin-etal-2022-cogktr
%X As the first step of modern natural language processing, text representation encodes discrete texts as continuous embeddings. Pre-trained language models (PLMs) have demonstrated strong ability in text representation and significantly promoted the development of natural language understanding (NLU). However, existing PLMs represent a text solely by its context, which is not enough to support knowledge-intensive NLU tasks. Knowledge is power, and fusing external knowledge explicitly into PLMs can provide knowledgeable text representations. Since previous knowledge-enhanced methods differ in many aspects, making it difficult for us to reproduce previous methods, implement new methods, and transfer between different methods. It is highly desirable to have a unified paradigm to encompass all kinds of methods in one framework. In this paper, we propose CogKTR, a knowledge-enhanced text representation toolkit for natural language understanding. According to our proposed Unified Knowledge-Enhanced Paradigm (UniKEP), CogKTR consists of four key stages, including knowledge acquisition, knowledge representation, knowledge injection, and knowledge application. CogKTR currently supports easy-to-use knowledge acquisition interfaces, multi-source knowledge embeddings, diverse knowledge-enhanced models, and various knowledge-intensive NLU tasks. Our unified, knowledgeable and modular toolkit is publicly available at GitHub, with an online system and a short instruction video.
%R 10.18653/v1/2022.emnlp-demos.1
%U https://aclanthology.org/2022.emnlp-demos.1
%U https://doi.org/10.18653/v1/2022.emnlp-demos.1
%P 1-11
Markdown (Informal)
[CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding](https://aclanthology.org/2022.emnlp-demos.1) (Jin et al., EMNLP 2022)
ACL
- Zhuoran Jin, Tianyi Men, Hongbang Yuan, Yuyang Zhou, Pengfei Cao, Yubo Chen, Zhipeng Xue, Kang Liu, and Jun Zhao. 2022. CogKTR: A Knowledge-Enhanced Text Representation Toolkit for Natural Language Understanding. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 1–11, Abu Dhabi, UAE. Association for Computational Linguistics.