Revisit Out-Of-Vocabulary Problem For Slot Filling: A Unified Contrastive Framework With Multi-Level Data Augmentations-Reference-Cited by-同舟云学术

Revisit Out-Of-Vocabulary Problem For Slot Filling: A Unified Contrastive Framework With Multi-Level Data Augmentations

Published:2023-06-04 Issue: Volume: Page:
ISSN:
Container-title:ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
language:
Short-container-title:

Author:

Guo Daichi¹,Dong Guanting¹,Fu Dayuan¹,Wu Yuxiang¹,Zeng Chen¹,Hui Tingfeng¹,Wang Liwen¹,Li Xuefeng¹,Wang Zechen¹,He Keqing²,Cui Xinyue¹,Xu Weiran¹

Affiliation:

1. Beijing University of Posts and Telecommunications,China

2. Meituan Group,Beijing,China

Publisher

IEEE

Link

Reference17 articles.

2. Representation learning with contrastive predictive coding;van den oord,2018

3. Snips voice platform: an embedded spoken language understanding system for private-by-design voice interfaces;coucke,2018

5. Supervised contrastive learning;khosla;Advances in neural information processing systems,2020

Cited by 5 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-Training for Noisy Slot Filling Task;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

3. Bridging the KB-Text Gap: Leveraging Structured Knowledge-aware Pre-training for KBQA;Proceedings of the 32nd ACM International Conference on Information and Knowledge Management;2023-10-21

4. A Multi-Task Semantic Decomposition Framework with Task-specific Pre-training for Few-Shot NER;Proceedings of the 32nd ACM International Conference on Information and Knowledge Management;2023-10-21