Next Article in Journal
Gradient and Parameter Dependent Dirichlet (p(x),q(x))-Laplace Type Problem
Next Article in Special Issue
Efficiency and Productivity of Local Educational Administration in Korea Using the Malmquist Productivity Index
Previous Article in Journal
Robust Detection and Modeling of the Major Temporal Arcade in Retinal Fundus Images
Previous Article in Special Issue
CAC: A Learning Context Recognition Model Based on AI for Handwritten Mathematical Symbols in e-Learning Systems
Article

Dense-to-Question and Sparse-to-Answer: Hybrid Retriever System for Industrial Frequently Asked Questions

1
Department of Computer Science and Engineering, Korea University, 145, Anam-ro, Seongbuk-gu, Seoul 02841, Korea
2
Human Inspired Artificial Intelligence Research (HIAI), Korea University, 145, Anam-ro, Seongbuk-gu, Seoul 02841, Korea
3
O2O Inc., 47, Maeheon-ro 8-gil, Seocho-gu, Seoul 06770, Korea
*
Author to whom correspondence should be addressed.
Academic Editor: Victor Mitrana
Mathematics 2022, 10(8), 1335; https://doi.org/10.3390/math10081335
Received: 21 March 2022 / Revised: 10 April 2022 / Accepted: 15 April 2022 / Published: 18 April 2022
The term “Frequently asked questions” (FAQ) refers to a query that is asked repeatedly and produces a manually constructed response. It is one of the most important factors influencing customer repurchase and brand loyalty; thus, most industry domains invest heavily in it. This has led to deep-learning-based retrieval models being studied. However, training a model and creating a database specializing in each industry domain comes at a high cost, especially when using a chatbot-based conversation system, as a large amount of resources must be continuously input for the FAQ system’s maintenance. It is also difficult for small- and medium-sized companies and national institutions to build individualized training data and databases and obtain satisfactory results. As a result, based on the deep learning information retrieval module, we propose a method of returning responses to customer inquiries using only data that can be easily obtained from companies. We hybridize dense embedding and sparse embedding in this work to make it more robust in professional terms, and we propose new functions to adjust the weight ratio and scale the results returned by the two modules. View Full-Text
Keywords: deep learning; artificial intelligence; natural language processing; frequently asked questions; dense and sparse embedding; industrial system; information retrieval deep learning; artificial intelligence; natural language processing; frequently asked questions; dense and sparse embedding; industrial system; information retrieval
Show Figures

Figure 1

MDPI and ACS Style

Seo, J.; Lee, T.; Moon, H.; Park, C.; Eo, S.; Aiyanyo, I.D.; Park, K.; So, A.; Ahn, S.; Park, J. Dense-to-Question and Sparse-to-Answer: Hybrid Retriever System for Industrial Frequently Asked Questions. Mathematics 2022, 10, 1335. https://doi.org/10.3390/math10081335

AMA Style

Seo J, Lee T, Moon H, Park C, Eo S, Aiyanyo ID, Park K, So A, Ahn S, Park J. Dense-to-Question and Sparse-to-Answer: Hybrid Retriever System for Industrial Frequently Asked Questions. Mathematics. 2022; 10(8):1335. https://doi.org/10.3390/math10081335

Chicago/Turabian Style

Seo, Jaehyung, Taemin Lee, Hyeonseok Moon, Chanjun Park, Sugyeong Eo, Imatitikua D. Aiyanyo, Kinam Park, Aram So, Sungmin Ahn, and Jeongbae Park. 2022. "Dense-to-Question and Sparse-to-Answer: Hybrid Retriever System for Industrial Frequently Asked Questions" Mathematics 10, no. 8: 1335. https://doi.org/10.3390/math10081335

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