Next Article in Journal
Real-Time Controller Design Test Bench for High-Voltage Direct Current Modular Multilevel Converters
Next Article in Special Issue
A Domain-Independent Classification Model for Sentiment Analysis Using Neural Models
Previous Article in Journal
Overview on Osteoporosis, Periodontitis and Oral Dysbiosis: The Emerging Role of Oral Microbiota
Previous Article in Special Issue
Zero-Shot Learning for Cross-Lingual News Sentiment Classification
Article

Incorporating Synonym for Lexical Sememe Prediction: An Attention-Based Model

1
School of Computer Science, China University of Geosciences, Wuhan 430074, China
2
School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, China
3
National Engineering Research Center for Geographic Information System, China University of Geosciences, Wuhan 430074, China
4
Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Natural Resources, Shenzhen 518034, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(17), 5996; https://doi.org/10.3390/app10175996
Received: 29 July 2020 / Revised: 24 August 2020 / Accepted: 27 August 2020 / Published: 29 August 2020
Sememe is the smallest semantic unit for describing real-world concepts, which improves the interpretability and performance of Natural Language Processing (NLP). To maintain the accuracy of the sememe description, its knowledge base needs to be continuously updated, which is time-consuming and labor-intensive. Sememes predictions can assign sememes to unlabeled words and are valuable work for automatically building and/or updating sememeknowledge bases (KBs). Existing methods are overdependent on the quality of the word embedding vectors, it remains a challenge for accurate sememe prediction. To address this problem, this study proposes a novel model to improve the performance of sememe prediction by introducing synonyms. The model scores candidate sememes from synonyms by combining distances of words in embedding vector space and derives an attention-based strategy to dynamically balance two kinds of knowledge from synonymous word set and word embedding vector. A series of experiments are performed, and the results show that the proposed model has made a significant improvement in the sememe prediction accuracy. The model provides a methodological reference for commonsense KB updating and embedding of commonsense knowledge. View Full-Text
Keywords: natural language processing; knowledge base; commonsense; sememe prediction; attention model natural language processing; knowledge base; commonsense; sememe prediction; attention model
Show Figures

Figure 1

MDPI and ACS Style

Kang, X.; Li, B.; Yao, H.; Liang, Q.; Li, S.; Gong, J.; Li, X. Incorporating Synonym for Lexical Sememe Prediction: An Attention-Based Model. Appl. Sci. 2020, 10, 5996. https://doi.org/10.3390/app10175996

AMA Style

Kang X, Li B, Yao H, Liang Q, Li S, Gong J, Li X. Incorporating Synonym for Lexical Sememe Prediction: An Attention-Based Model. Applied Sciences. 2020; 10(17):5996. https://doi.org/10.3390/app10175996

Chicago/Turabian Style

Kang, Xiaojun, Bing Li, Hong Yao, Qingzhong Liang, Shengwen Li, Junfang Gong, and Xinchuan Li. 2020. "Incorporating Synonym for Lexical Sememe Prediction: An Attention-Based Model" Applied Sciences 10, no. 17: 5996. https://doi.org/10.3390/app10175996

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop