Next Article in Journal
Evaluating Passenger Demand for Development of the Urban Transport System by an AHP Model with the Real-World Application of Amman
Next Article in Special Issue
Assessment of Word-Level Neural Language Models for Sentence Completion
Previous Article in Journal
Remediation of Organically Contaminated Soil Through the Combination of Assisted Phytoremediation and Bioaugmentation
Previous Article in Special Issue
A Text Abstraction Summary Model Based on BERT Word Embedding and Reinforcement Learning
Open AccessArticle

Reliable Classification of FAQs with Spelling Errors Using an Encoder-Decoder Neural Network in Korean

Program of Computer and Communications Engineering, Kangwon National University, Chuncheon 24341, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2019, 9(22), 4758; https://doi.org/10.3390/app9224758
Received: 7 October 2019 / Revised: 30 October 2019 / Accepted: 3 November 2019 / Published: 7 November 2019
To resolve lexical disagreement problems between queries and frequently asked questions (FAQs), we propose a reliable sentence classification model based on an encoder-decoder neural network. The proposed model uses three types of word embeddings; fixed word embeddings for representing domain-independent meanings of words, fined-tuned word embeddings for representing domain-specific meanings of words, and character-level word embeddings for bridging lexical gaps caused by spelling errors. It also uses class embeddings to represent domain knowledge associated with each category. In the experiments with an FAQ dataset about online banking, the proposed embedding methods contributed to an improved performance of the sentence classification. In addition, the proposed model showed better performance (with an accuracy of 0.810 in the classification of 411 categories) than that of the comparison model. View Full-Text
Keywords: FAQ classification; encoder-decoder neural network; multi-level word embeddings FAQ classification; encoder-decoder neural network; multi-level word embeddings
Show Figures

Figure 1

MDPI and ACS Style

Jang, Y.; Kim, H. Reliable Classification of FAQs with Spelling Errors Using an Encoder-Decoder Neural Network in Korean. Appl. Sci. 2019, 9, 4758. https://doi.org/10.3390/app9224758

AMA Style

Jang Y, Kim H. Reliable Classification of FAQs with Spelling Errors Using an Encoder-Decoder Neural Network in Korean. Applied Sciences. 2019; 9(22):4758. https://doi.org/10.3390/app9224758

Chicago/Turabian Style

Jang, Youngjin; Kim, Harksoo. 2019. "Reliable Classification of FAQs with Spelling Errors Using an Encoder-Decoder Neural Network in Korean" Appl. Sci. 9, no. 22: 4758. https://doi.org/10.3390/app9224758

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
Search more from Scilit
 
Search
Back to TopTop