지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- Korean Institute of Information Scientists and Engineers Journal of Computing Science and Engineering Journal of Computing Science and Engineering Vol.16 No.2
- 발행연도
- 2022.6
- 수록면
- 63 - 78 (16page)
- DOI
- 10.5626/JCSE.2022.16.2.63
이용수
초록· 키워드
오류제보하기
Natural language understanding (NLU) is a fundamental technology for implementing natural interfaces. The embedding of sentences and correspondence between text and its extracted semantic knowledge, called semantic frame, has recently shown that a semantic vector representation is key in the implementation or support of robust NLU systems. Herein, we propose an extension of cluster-aware modeling with various types of pre-trained transformers for consideration of the many-to-1 relationships of text-to-semantic frames and semantic clusters. To attain this, we define the semantic cluster, and design the relationships between cluster members to learn semantically meaningful vector representations. In addition, we introduce novel ensemble methods to improve the semantic vector applications around NLU, i.e., similarity-based intent classification and a semantic search. Furthermore, novel semantic vector and corpus visualization techniques are presented. Using the proposed framework, we demonstrate that the proposed model can learn meaningful semantic vector representations in ATIS, SNIPS, SimM, and Weather datasets.
목차
Abstract
I. INTRODUCTION
II. SEMANTIC FRAME SENTENCES AND SEMANTIC CLUSTERS
III. CLUSTER-AWARE SEMANTIC VECTOR LEARNING
IV. APPLICATIONS
V. EXPERIMENTS
VI. RELATED STUDIES
VII. CONCLUSION
REFERENCES
참고문헌 (23)
참고문헌 신청
S. Jung, J. Lee, and J. Kim, “Learning to embed semantic correspondence for natural language understanding,” in Proceedings of the 22nd Conference on Computational Natural Language Learning, Brussels, Belgium, 2018, pp. 131-140.
S. Jung, “Semantic vector learning for natural language understanding,” Computer Speech & Language, vol. 56, pp. 130-145, 2019.
S. Jung, “Semantic vector learning using pretrained transformers in natural language understanding,” Journal of Computing Science and Engineering, vol. 14, no. 4, pp. 154-162, 2020.
S. Jung and S. Lim, “Cluster-aware semantic vector learning using BERT in natural language understanding,” in Proceedings of 2021 IEEE International Conference on Big Data and Smart Computing (BigComp), Jeju, South Korea, 2021, pp. 91-98.
J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Minneapolis, MN, 2018, pp. 4171-4186.
S. Jung, “Semantic vector learning for natural language understanding,” Computer Speech & Language, vol. 56, pp. 130-145, 2019.
S. Jung, “Semantic vector learning using pretrained transformers in natural language understanding,” Journal of Computing Science and Engineering, vol. 14, no. 4, pp. 154-162, 2020.
S. Jung and S. Lim, “Cluster-aware semantic vector learning using BERT in natural language understanding,” in Proceedings of 2021 IEEE International Conference on Big Data and Smart Computing (BigComp), Jeju, South Korea, 2021, pp. 91-98.
J. Devlin, M. W. Chang, K. Lee, and K. Toutanova, “BERT: pre-training of deep bidirectional transformers for language understanding,” in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Minneapolis, MN, 2018, pp. 4171-4186.
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Semantic Vector Learning Using Pretrained Transformers in Natural Language Understanding
Journal of Computing Science and Engineering
2020 .12
-
Low-Dimensional Vector Representation Learning for Text Visualization Using Task-Oriented Dialogue Dataset
Journal of Computing Science and Engineering
2022 .09
-
자연어이해 영역에서의 관계성 학습을 통한 유사구조 문장 벡터 학습방법
정보과학회 컴퓨팅의 실제 논문지
2021 .04
-
Semantic Similarity-based Intent Analysis using Pre-trained Transformer for Natural Language Understanding
Journal of KIISE
2020 .08
-
Decoupled SVPWM for Five-Phase Permanent Magnet Machines with Trapezoidal Back-EMF
JOURNAL OF POWER ELECTRONICS
2018 .09
-
Visual Attention by Scr een Vectors : Independent, Continuing, Converging, and Diverging Vectors
멀티미디어학회논문지
2015 .10
-
클러스터 사업성과를 위한 지원 체계의 요인에 관한 연구
유공압건설기계학회 학술대회논문집
2019 .11
-
선형변환된 i-vector를 이용한 DNN 음향모델의 화자적응
대한전자공학회 학술대회
2016 .06
-
Cluster-based Protocol with Improved Cluster Formation Method
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2019 .06
-
Multi-task Learning Approach Based on Pre-trained Language Models Using Temporal Relations
Journal of KIISE
2023 .01
-
Speaker Diarization Using Multi-Modal i-vectors
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications
2015 .06
-
스마트 헬스케어를 위한 바이오 벡터 생성 프레임워크
한국컴퓨터정보학회논문지
2016 .01
-
Ensemble of Support Vector Machine and Meta classification
한국통신학회 학술대회논문집
2018 .06
-
의미틀 저차원 좌표변환 및 회귀 기반 의미벡터 학습 방법
한국정보과학회 학술발표논문집
2020 .07
-
특징공간에서의 군집화 유효성 지수의 개발
대한산업공학회지
2020 .08
-
Current Dynamically Predicting Control of PMSM Targeting the Current Vectors
Journal of Electrical Engineering & Technology
2015 .05
-
New Generalized SVPWM Algorithm for Multilevel Inverters
JOURNAL OF POWER ELECTRONICS
2018 .07
-
Support Vector Machine 기반 부분방전 진단 기법 개발
전력전자학회 학술대회 논문집
2023 .07
-
Effects of Variability of Time-varying Segment-to-joint Vectors on Estimation Accuracy of Relative Position between Body Segments
한국정밀공학회 학술발표대회 논문집
2021 .05
-
Robust Algorithms for Combining Multiple Term Weighting Vectors for Document Classification
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2016 .06
이 논문의 저자 정보
최근 본 자료
댓글(0)
0