Zero-Shot Learners for Natural Language Understanding via a Unified Multiple-Choice Perspective
Zero-shot learning is an approach where models generalize to unseen tasks without direct training on them. We introduce the Unified Multiple-Choice (UniMC) framework, which is format-independent, compatible with various formats, and applicable to tasks like text classification and sentiment analysis...
Egile Nagusiak: | Junjie Wang, Ping Yang, Ruyi Gan, Yuxiang Zhang, Jiaxing Zhang, Tetsuya Sakai |
---|---|
Formatua: | Artikulua |
Hizkuntza: | English |
Argitaratua: |
IEEE
2023-01-01
|
Saila: | IEEE Access |
Gaiak: | |
Sarrera elektronikoa: | https://ieeexplore.ieee.org/document/10359522/ |
Antzeko izenburuak
-
Hand and Pose-Based Feature Selection for Zero-Shot Sign Language Recognition
nork: Giray Sercan Ozcan, et al.
Argitaratua: (2024-01-01) -
Temporal–Semantic Aligning and Reasoning Transformer for Audio-Visual Zero-Shot Learning
nork: Kaiwen Zhang, et al.
Argitaratua: (2024-07-01) -
Multi-Label Zero-Shot Learning With Adversarial and Variational Techniques
nork: Muqaddas Gull, et al.
Argitaratua: (2024-01-01) -
Focusing on Valid Search Space in Open-World Compositional Zero-Shot Learning by Leveraging Misleading Answers
nork: Soohyeong Kim, et al.
Argitaratua: (2024-01-01) -
Hybrid attentive prototypical network for few-shot action recognition
nork: Zanxi Ruan, et al.
Argitaratua: (2024-08-01)