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.14 No.4
- 발행연도
- 2020.12
- 수록면
- 154 - 162 (9page)
- DOI
- 10.5626/JCSE.2020.14.4.154
이용수
초록· 키워드
오류제보하기
Natural language understanding (NLU) is a core technology for implementing natural interfaces. To implement and support robust NLU, previous studies introduced a neural network approach to learn semantic vector representation by employing the correspondence between text and semantic frame texts as extracted semantic knowledge. In their work, long short-term memory (LSTM)-based text and readers were used to encode both text and semantic frames. However, there exists significant room for performance improvement using recent pretrained transformer encoders. In the present work, as a key contribution, we have extended Jung"s framework to work with pretrained transformers for both text and semantic frame readers. In particular, a novel semantic frame processing method is proposed to directly feed the structural form of the semantic frame to transformers. We conducted massive experiments by combining various types of LSTM- or transformer-based text and semantic frame readers on the ATIS, SNIPS, Sim-M, Sim-R, and Weather datasets to find the best suitable configurations for learning effective semantic vector representations. Through the experiments, we concluded that the transformer-based text and semantic frame reader show a stable and rapid learning curve as well as the best performance in similarity-based intent classification and semantic search tasks.
목차
Abstract
I. INTRODUCTION
II. SEMANTIC VECTOR LEARNING WITH A PRETRAINED TRANSFORMER
III. EXPERIMENTS
IV. RELATED WORK
V. CONCLUSION
REFERENCES
참고문헌 (20)
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, H. Suh, H. J. Kim, and T. W. Hwang, “Semantic similarity-based intent analysis using pretrained transformer for natural language understanding,” Journal of KIISE, vol. 47, no. 8, pp. 748-760, 2020.
H. Kim and S. Jung, “Semantic vector learning using pretrained BERT,” in Proceeding of the Korea Software Congress, Pyeongchang, Korea, 2019, pp. 1427-1429.
T. W. Hwang, S. Jung, H. Suh, and H. J. Kim, “Low dimensional semantic frame transformation method and regression-based semantic vector learning,” in Proceeding of the Korea Computer Congress, Busan, Korea, 2020, pp. 341-343.
S. Jung, “Semantic vector learning for natural language understanding,” Computer Speech & Language, vol. 56, pp. 130-145, 2019.
S. Jung, H. Suh, H. J. Kim, and T. W. Hwang, “Semantic similarity-based intent analysis using pretrained transformer for natural language understanding,” Journal of KIISE, vol. 47, no. 8, pp. 748-760, 2020.
H. Kim and S. Jung, “Semantic vector learning using pretrained BERT,” in Proceeding of the Korea Software Congress, Pyeongchang, Korea, 2019, pp. 1427-1429.
T. W. Hwang, S. Jung, H. Suh, and H. J. Kim, “Low dimensional semantic frame transformation method and regression-based semantic vector learning,” in Proceeding of the Korea Computer Congress, Busan, Korea, 2020, pp. 341-343.
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Semantic Vector Learning and Visualization with Semantic Cluster Using Transformers in Natural Language Understanding
Journal of Computing Science and Engineering
2022 .06
-
Image-Text 멀티모달 변환을 통한 의미 전달 기반 Semantic 통신
한국통신학회 학술대회논문집
2023 .06
-
Enhancing semantically masked Transformer with local attention for semantic segmentation
한국자동차공학회 춘계학술대회
2024 .06
-
의미틀 저차원 좌표변환 및 회귀 기반 의미벡터 학습 방법
한국정보과학회 학술발표논문집
2020 .07
-
“자연어 의미분석”특집을 내면서
정보과학회지
2016 .08
-
Semantic-Aware Shadow Removing Transformer With Prompt-Based Method
한국방송미디어공학회 학술발표대회 논문집
2024 .06
-
다중 패치를 이용한 트랜스포머 기반 장면 텍스트 인식
제어로봇시스템학회 논문지
2022 .10
-
A Study on the Semantic Communication Systems
한국통신학회 학술대회논문집
2024 .11
-
Semantic Similarity-based Intent Analysis using Pre-trained Transformer for Natural Language Understanding
Journal of KIISE
2020 .08
-
Semantic Segmentation 기술 동향에 대한 연구
한국정보과학회 학술발표논문집
2020 .07
-
A Review of Multi-User Semantic Communication
한국통신학회 학술대회논문집
2024 .06
-
Semantic Mapping Based on Image Feature Fusion in Indoor Environments
제어로봇시스템학회 국제학술대회 논문집
2021 .10
-
The semantic consideration on strategic decision making
대한산업공학회 춘계공동학술대회 논문집
2019 .04
-
A Semantic Aspect-Based Vector Space Model to Identify the Event Evolution Relationship within Topics
Journal of Computing Science and Engineering
2015 .06
-
한국어 의미 분석을 위한 세종의미망 확장
한국정보과학회 학술발표논문집
2016 .12
-
A Review of the Quantum Semantic Systems
한국통신학회 학술대회논문집
2024 .06
-
[게재논문 수정] 트랜스포머 기반 산림지와 도심지 의미론적 분할 및 탄소 저장량 예측 기법
디지털콘텐츠학회논문지
2025 .02
-
변압기 효율 적정화를 위한 변압기 부하율 조사 및 추정
조명·전기설비학회논문지
2016 .01
-
선학습 BERT를 활용한 의미벡터 학습 방법
한국정보과학회 학술발표논문집
2019 .12
-
기술의 의미관계 분석 모델 개발
대한산업공학회 추계학술대회 논문집
2020 .11
이 논문의 저자 정보
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0