Aspect-based sentiment analysis (ABSA) involves identifying sentiment toward specific aspect terms in a sentence and allows us to uncover people's nuanced perspectives and attitudes on particular aspects of a prod...
详细信息
Aspect-based sentiment analysis (ABSA) involves identifying sentiment toward specific aspect terms in a sentence and allows us to uncover people's nuanced perspectives and attitudes on particular aspects of a product, service, or topic. However, the scarcity of labeled data poses a significant challenge to training high-quality models. To address this issue, we explore the potential of dataaugmentation using ChatGPT, a well-performing large language model, to enhance the sentiment classification performance toward aspect terms. Specifically, we explore three dataaugmentation strategies based on ChatGPT: context-focused, aspect-focused, and context-aspect dataaugmentation techniques. Context-focused dataaugmentation focuses on changing the word expression of context words in the sentence while keeping aspect terms unchanged. In contrast, aspect-focused dataaugmentation aims to change aspect terms but keep context words unchanged. Context-aspect dataaugmentation integrates these two dataaugmentations to generate augmented samples. Furthermore, we incorporate contrastive learning into the ABSA tasks to improve performance. Extensive experiments show that all three dataaugmentation techniques lead to performance improvements, with the context-aspect dataaugmentation strategy performing best and surpassing the performance of the baseline models.
Driver identification using in-vehicle data is receiving considerable attention in the field of intelligent transportation owing to the advances in deep learning (DL). In order to improve accuracy and robustness of id...
详细信息
Driver identification using in-vehicle data is receiving considerable attention in the field of intelligent transportation owing to the advances in deep learning (DL). In order to improve accuracy and robustness of identification, this paper proposes an ensemble deep learning framework that integrates a modified one-dimensional convolutional neural network (M 1-D CNN) and bidirectional long short-term memory (BLSTM) to improve the performance and robustness of driver identification using information extracted from vehicular CAN-bus signals. The M 1-D CNN architecture is developed by adopting inception blocks, residual connection, and global average pooling to obtain optimal deep-feature representations of local time series. The BLSTM is used to learn the bidirectional long-term temporal dependencies. Results of extensive experiments using real driving data show that the proposed ensemble DL model can improve the accuracy and robustness of driver identification. Furthermore, four data augmentation methods, namely up-sampling, adding noise, data reversal, and random drifting, are used to expand the original training data to improve the performance of the ensemble method. Especially, few-shot learning is performed using the four data augmentation methods, and it shows excellent potential for driver identification with limited data.
作者：
Lee, JCAjou Univ
Dept Syst Engn Yongin 449820 Kyonggido South Korea Inst Adv Engn
Yongin 449820 Kyonggido South Korea
The implementation of forward/backward least mean square linear predictors in the frequency-domain is known to require two DFT/FFT operations. Were, computationally efficient structures are derived using proper data a...
详细信息
The implementation of forward/backward least mean square linear predictors in the frequency-domain is known to require two DFT/FFT operations. Were, computationally efficient structures are derived using proper data augmentation methods. As a result, the Following are achieved: (i) reduction of a DFT/FFT operation: and (ii) further reduction ill complexity when the input signal is real-valued.
暂无评论