Meta-learning approaches for few-shot learning: A survey of recent advances
Despite its astounding success in learning deeper multi-dimensional data, the performance
of deep learning declines on new unseen tasks mainly due to its focus on same-distribution …
of deep learning declines on new unseen tasks mainly due to its focus on same-distribution …
A review of text corpus-based tourism big data mining
With the massive growth of the Internet, text data has become one of the main formats of
tourism big data. As an effective expression means of tourists' opinions, text mining of such …
tourism big data. As an effective expression means of tourists' opinions, text mining of such …
Meta-learning for few-shot natural language processing: A survey
W Yin - arXiv preprint arXiv:2007.09604, 2020 - arxiv.org
Few-shot natural language processing (NLP) refers to NLP tasks that are accompanied with
merely a handful of labeled examples. This is a real-world challenge that an AI system must …
merely a handful of labeled examples. This is a real-world challenge that an AI system must …
A two-step data augmentation method based on generative adversarial network for hardness prediction of high entropy alloy
Z Yang, S Li, S Li, J Yang, D Liu - Computational Materials Science, 2023 - Elsevier
The machine learning (ML) has been widely applied in materials science research and has
made a lot of contributions. However, the performance of ML model is limited by the amount …
made a lot of contributions. However, the performance of ML model is limited by the amount …
Dynamic memory induction networks for few-shot text classification
This paper proposes Dynamic Memory Induction Networks (DMIN) for few-shot text
classification. The model utilizes dynamic routing to provide more flexibility to memory …
classification. The model utilizes dynamic routing to provide more flexibility to memory …
A closer look at feature space data augmentation for few-shot intent classification
New conversation topics and functionalities are constantly being added to conversational AI
agents like Amazon Alexa and Apple Siri. As data collection and annotation is not scalable …
agents like Amazon Alexa and Apple Siri. As data collection and annotation is not scalable …
Recent advances of few-shot learning methods and applications
JY Wang, KX Liu, YC Zhang, B Leng, JH Lu - Science China Technological …, 2023 - Springer
The rapid development of deep learning provides great convenience for production and life.
However, the massive labels required for training models limits further development. Few …
However, the massive labels required for training models limits further development. Few …
Frog-GNN: Multi-perspective aggregation based graph neural network for few-shot text classification
S Xu, Y Xiang - Expert Systems with Applications, 2021 - Elsevier
Few-shot text classification aims to learn a classifier from very few labeled text instances per
class. Previous few-shot research works in NLP are mainly based on Prototypical Networks …
class. Previous few-shot research works in NLP are mainly based on Prototypical Networks …
Out-of-domain detection for low-resource text classification tasks
Out-of-domain (OOD) detection for low-resource text classification is a realistic but
understudied task. The goal is to detect the OOD cases with limited in-domain (ID) training …
understudied task. The goal is to detect the OOD cases with limited in-domain (ID) training …
Clur: Uncertainty estimation for few-shot text classification with contrastive learning
Few-shot text classification has extensive application where the sample collection is
expensive or complicated. When the penalty for classification errors is high, such as early …
expensive or complicated. When the penalty for classification errors is high, such as early …