상품 카테고리 자동분류를 위한 BERT-분류기 아키텍처 연구 = Research on a BERT-Classifier Architecture for Automatic Product Category Classification

다국어 초록 (Multilingual Abstract)

This research focuses on an architecture that vectorizes the names of various products found in daily life using BERT, followed by predicting product categories based on these embeddings. The architecture's performance is determined by the BERT model, which extracts embeddings from product names, and the classifier that predicts categories from these embeddings. Consequently, this research initially aimed to identify a BERT model suitable for classifying product names and then find the most efficient combination of BERT model and classifier by applying various classifiers to the chosen BERT model. A simple CNN classifier was employed for the initial selection of a suitable BERT model, serving as a baseline for performance comparison with other classifiers. The architecture's effectiveness was quantified using precision, recall, f1 score, and accuracy for category predictions. Experimental results showed that the Sentence BERT model was more suitable for this task than a conventional BERT model. Additionally, classifiers enhanced with Residual Blocks demonstrated superior performance compared to the baseline combination of Sentence BERT and CNN. The Sentence BERT model used in this study, not trained on Korean data, suggests that further improvements could be achieved through Domain Adaptation by training with diverse Korean datasets.

참고문헌 (Reference)

1 Park, D., "The Impact of Stopwords on BERT-Based Automatic Sentence Classifier (불용어의 BERT 기반 문장 자동분류기에 대한 영향)" 715-717, 2021

2 Reimers, N., "Sentence-bert: Sentence embeddings using siamese bert-networks"

3 Kim, B., "Sentence BERT for Measuring Sentence Similarity in Korean (한국어 문장 유사도 측정을 위한 Sentence BERT)" 1376-1378, 2020

4 Lim, J. H., "Recent r&d trends for pretrained language model(딥러닝 사전학습 언어모델 기술 동향)" 35 (35): 9-19, 2020

5 Park, S., "Klue: Korean language understanding evaluation"

6 Lee, J., "Kcbert: Korean comments bert" 437-440, 2020

7 Krizhevsky, A., "Imagenet classification with deep convolutional neural networks" 25 : 2012

8 Lim, J., "Hypernews Detection using Sentence BERT Embedding" 388-391, 2019

9 He, K., "Deep residual learning for image recognition" 770-778, 2016

10 Devlin, J., "Bert: Pre-training of deep bidirectional transformers for language understanding"

11 Vaswani, A., "Attention is all you need" 30 : 2017

12 Li, Z., "Analyzing overfitting under class imbalance in neural networks for image segmentation" 40 (40): 1065-1077, 2020

13 송장섭 ; 류성열, "An Empirical Study on Quality Improvement by Data Standardization for Distributed Goods(유통 상품의 데이터 품질 관리를 위한 데이터 표준화에 대한 연구)" 18 (18): 101-109, 2013