The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Sememe은 인간 언어의 가장 작은 의미 단위로, 그 구성은 단어의 의미를 나타낼 수 있습니다. Sememes는 자연어 처리(NLP) 분야의 많은 다운스트림 애플리케이션에 성공적으로 적용되었습니다. 단어의 의미에 대한 주석은 언어 전문가에 의존하기 때문에 시간과 노동력이 많이 소모되어 대규모의 의미적 적용에 한계가 있습니다. 연구자들은 단어의 의미를 자동으로 예측하는 몇 가지 의미 예측 방법을 제안했습니다. 그러나 기존의 의미 예측 방법은 단어 간의 관계를 나타내는 전문가의 주석이 달린 지식 기반을 무시하고 단어 자체의 정보에만 초점을 맞추고 의미 예측에서 가치를 두어야 합니다. 따라서 우리는 전문가가 주석을 단 지식 기반을 sememe 예측 프로세스에 통합하는 것을 목표로 합니다. 이를 달성하기 위해 우리는 관계형 관점에서 sememe 예측을 재구성하기 위해 기존 단어 지식 기반 CilinE를 사용하는 CilinE 기반 sememe 예측 모델을 제안합니다. 널리 사용되는 중국 sememe 지식 기반인 HowNet에 대한 실험에서는 CilinE가 sememe 예측에 명백히 긍정적인 영향을 미치는 것으로 나타났습니다. 또한 제안한 방법은 기존 방법과 통합되어 예측 성능을 크게 향상시킬 수 있습니다. 우리는 데이터와 코드를 대중에게 공개할 것입니다.
Hao WANG
North China University of Technology,Beijing Urban Governance Research Center,CNONIX National Standard Application and Promotion Lab
Sirui LIU
North China University of Technology,CNONIX National Standard Application and Promotion Lab
Jianyong DUAN
North China University of Technology,CNONIX National Standard Application and Promotion Lab
Li HE
North China University of Technology,CNONIX National Standard Application and Promotion Lab
Xin LI
North China University of Technology,CNONIX National Standard Application and Promotion Lab
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
부
Hao WANG, Sirui LIU, Jianyong DUAN, Li HE, Xin LI, "Chinese Lexical Sememe Prediction Using CilinE Knowledge" in IEICE TRANSACTIONS on Fundamentals,
vol. E106-A, no. 2, pp. 146-153, February 2023, doi: 10.1587/transfun.2022EAP1074.
Abstract: Sememes are the smallest semantic units of human languages, the composition of which can represent the meaning of words. Sememes have been successfully applied to many downstream applications in natural language processing (NLP) field. Annotation of a word's sememes depends on language experts, which is both time-consuming and labor-consuming, limiting the large-scale application of sememe. Researchers have proposed some sememe prediction methods to automatically predict sememes for words. However, existing sememe prediction methods focus on information of the word itself, ignoring the expert-annotated knowledge bases which indicate the relations between words and should value in sememe predication. Therefore, we aim at incorporating the expert-annotated knowledge bases into sememe prediction process. To achieve that, we propose a CilinE-guided sememe prediction model which employs an existing word knowledge base CilinE to remodel the sememe prediction from relational perspective. Experiments on HowNet, a widely used Chinese sememe knowledge base, have shown that CilinE has an obvious positive effect on sememe prediction. Furthermore, our proposed method can be integrated into existing methods and significantly improves the prediction performance. We will release the data and code to the public.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2022EAP1074/_p
부
@ARTICLE{e106-a_2_146,
author={Hao WANG, Sirui LIU, Jianyong DUAN, Li HE, Xin LI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Chinese Lexical Sememe Prediction Using CilinE Knowledge},
year={2023},
volume={E106-A},
number={2},
pages={146-153},
abstract={Sememes are the smallest semantic units of human languages, the composition of which can represent the meaning of words. Sememes have been successfully applied to many downstream applications in natural language processing (NLP) field. Annotation of a word's sememes depends on language experts, which is both time-consuming and labor-consuming, limiting the large-scale application of sememe. Researchers have proposed some sememe prediction methods to automatically predict sememes for words. However, existing sememe prediction methods focus on information of the word itself, ignoring the expert-annotated knowledge bases which indicate the relations between words and should value in sememe predication. Therefore, we aim at incorporating the expert-annotated knowledge bases into sememe prediction process. To achieve that, we propose a CilinE-guided sememe prediction model which employs an existing word knowledge base CilinE to remodel the sememe prediction from relational perspective. Experiments on HowNet, a widely used Chinese sememe knowledge base, have shown that CilinE has an obvious positive effect on sememe prediction. Furthermore, our proposed method can be integrated into existing methods and significantly improves the prediction performance. We will release the data and code to the public.},
keywords={},
doi={10.1587/transfun.2022EAP1074},
ISSN={1745-1337},
month={February},}
부
TY - JOUR
TI - Chinese Lexical Sememe Prediction Using CilinE Knowledge
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 146
EP - 153
AU - Hao WANG
AU - Sirui LIU
AU - Jianyong DUAN
AU - Li HE
AU - Xin LI
PY - 2023
DO - 10.1587/transfun.2022EAP1074
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E106-A
IS - 2
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - February 2023
AB - Sememes are the smallest semantic units of human languages, the composition of which can represent the meaning of words. Sememes have been successfully applied to many downstream applications in natural language processing (NLP) field. Annotation of a word's sememes depends on language experts, which is both time-consuming and labor-consuming, limiting the large-scale application of sememe. Researchers have proposed some sememe prediction methods to automatically predict sememes for words. However, existing sememe prediction methods focus on information of the word itself, ignoring the expert-annotated knowledge bases which indicate the relations between words and should value in sememe predication. Therefore, we aim at incorporating the expert-annotated knowledge bases into sememe prediction process. To achieve that, we propose a CilinE-guided sememe prediction model which employs an existing word knowledge base CilinE to remodel the sememe prediction from relational perspective. Experiments on HowNet, a widely used Chinese sememe knowledge base, have shown that CilinE has an obvious positive effect on sememe prediction. Furthermore, our proposed method can be integrated into existing methods and significantly improves the prediction performance. We will release the data and code to the public.
ER -