Few-Shot Text Classification with Global–Local Feature Information

Advances in Intelligent Systems and Computing

2021

Current state-of-the-art approaches for few-shot action recognition achieve promising performance by conducting frame-level matching on learned visual features. However, they generally suffer from two limitations: i) the matching procedure between local frames tends to be inaccurate due to the lack of guidance to force long-range temporal perception; ii) explicit motion learning is usually ignored, leading to partial information loss. To address these issues, we develop a Motion-augmented Long-short Contrastive Learning (MoLo) method that contains two crucial components, including a long-short contrastive objective and a motion autodecoder. Specifically, the long-short contrastive objective is to endow local frame features with long-form temporal awareness by maximizing their agreement with the global token of videos belonging to the same class. The motion autodecoder is a lightweight architecture to reconstruct pixel motions from the differential features, which explicitly embeds the network with motion dynamics. By this means, MoLo can simultaneously learn long-range temporal context and motion cues for comprehensive few-shot matching. To demonstrate the effectiveness, we evaluate MoLo on five standard benchmarks, and the results show that MoLo favorably outperforms recent advanced methods. The source code is available at https://github. com/alibaba-mmai-research/MoLo.

Section: Introductionmentioning

confidence: 99%

Key Technology of Automation Control Based on Artificial Intelligence Technology

Advances in Intelligent Systems and Computing

2021

A Chinese Few-Shot Text Classification Method Utilizing Improved Prompt Learning and Unlabeled Data

Chen

et al. 2023

Applied Sciences

Insufficiently labeled samples and low-generalization performance have become significant natural language processing problems, drawing significant concern for few-shot text classification (FSTC). Advances in prompt learning have significantly improved the performance of FSTC. However, prompt learning methods typically require the pre-trained language model and tokens of the vocabulary list for model training, while different language models have different token coding structures, making it impractical to build effective Chinese prompt learning methods from previous approaches related to English. In addition, a majority of current prompt learning methods do not make use of existing unlabeled data, thus often leading to unsatisfactory performance in real-world applications. To address the above limitations, we propose a novel Chinese FSTC method called CIPLUD that combines an improved prompt learning method and existing unlabeled data, which are used for the classification of a small amount of Chinese text data. We used the Chinese pre-trained language model to build two modules: the Multiple Masks Optimization-based Prompt Learning (MMOPL) module and the One-Class Support Vector Machine-based Unlabeled Data Leveraging (OCSVM-UDL) module. The former generates prompt prefixes with multiple masks and constructs suitable prompt templates for Chinese labels. It optimizes the random token combination problem during label prediction with joint probability and length constraints. The latter, by establishing an OCSVM model in the trained text vector space, selects reasonable pseudo-label data for each category from a large amount of unlabeled data. After selecting the pseudo-label data, we mixed them with the previous few-shot annotated data to obtain brand new training data and then repeated the steps of the two modules as an iterative semi-supervised optimization process. The experimental results on the four Chinese FSTC benchmark datasets demonstrate that our proposed solution outperformed other prompt learning methods with an average accuracy improvement of 2.3%.

Fairness-aware genetic-algorithm-based few-shot classification

Cheng

2022

MBE

<abstract><p>Artificial-intelligence-assisted decision-making is appearing increasingly more frequently in our daily lives; however, it has been shown that biased data can cause unfairness in decision-making. In light of this, computational techniques are needed to limit the inequities in algorithmic decision-making. In this letter, we present a framework to join fair feature selection and fair meta-learning to do few-shot classification, which contains three parts: (1) a pre-processing component acts as an intermediate bridge between fair genetic algorithm (FairGA) and fair few-shot (FairFS) to generate the feature pool; (2) the FairGA module considers the presence or absence of words as gene expression, and filters out key features by a fairness clustering genetic algorithm; (3) the FairFS part carries out the task of representation and fairness constraint classification. Meanwhile, we propose a combinatorial loss function to cope with fairness constraints and hard samples. Experiments show that the proposed method achieves strong competitive performance on three public benchmarks.</p></abstract>