ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 CNN based Sentence Classification with Semantic Features using Word Clustering
Cited 4 time in scopus Download 2 time Share share facebook twitter linkedin kakaostory
저자
김화연, 이진수, 여나영, 마셀라, 이승익, 김영길
발행일
201810
출처
International Conference on Information and Communication Technology Convergence (ICTC) 2018, pp.484-488
DOI
https://dx.doi.org/10.1109/ICTC.2018.8539546
협약과제
18HS3700, 언어학습을 위한 자유발화형 음성대화처리 원천기술 개발, 이윤근
초록
Text classification is one of the natural language processing (NLP) methods that assigns texts to one or more categories. In this paper, we propose a text classification method based on deep neural networks and word clustering. We also provide analysis on the effects of the number of channels, the way of converting the cluster information to a vector, and the update method of the input channel during learning with baseline. To show the effectiveness of our approach, we apply the method to the TREC question dataset and Movie Review dataset. From the results, we confirm that semantic features from word clustering is able to increase the classification accuracy by 1.96%.
키워드
Convolutional Neural Networks, Deep learning, Sentence classification, Word clustering
KSP 제안 키워드
Classification method, Cluster information, Convolution neural network(CNN), Deep neural network(DNN), Movie Review, Natural Language Processing, Sentence Classification, Word clustering, classification accuracy, deep learning(DL), semantic features