北京邮电大学计算机视觉博士,双锴教授博导/硕导

最新推荐文章于 2023-07-04 16:00:38 发布

邓炯源

最新推荐文章于 2023-07-04 16:00:38 发布

阅读量779

点赞数

文章标签：北京邮电大学计算机视觉博士

本文综述了近年来深度学习在自然语言处理领域的关键成果，包括基于LSTM的长短期记忆模型、多原型融合的卷积-解卷积词嵌入方法、神经网络驱动的文本分类和情感分析技术。重点介绍了注意力机制和位置感知的双LSTM模型(AELA-DLSTMs)以及用于情感信息收集和提取的架构。文章还探讨了机器理解中的全局视角——SummaryFilter，展示了深度学习在机器 comprehension 中的应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

部分第一作者论文

[1] Major-minor long short-term memory for word-level language model. IEEE Transactions on Neural Networks and Learning Systems. 2019.12. 1:15

[2] Convolution–deconvolution word embedding: An end-to-end multi-prototype fusion embedding method for natural language processing, Information Fusion, 2020.1.1. 53:112-122.

[3] A word-building method based on neural network for text classification, Journal of Experimental & Theoretical Artificial Intelligence, 2019.1.30, 2019:1-20.

[4] AELA-DLSTMs: Attention-Enabled and Location-Aware Double LSTMs for aspect-level sentiment classification, Neurocomputing, 2018.12.30, 334:25-34

[5] A sentiment information Collector–Extractor architecture based neural network for sentiment analysis, Information Sciences, 2018.10, 467:549-558.

[6] Summarization Filter: Consider More About the Whole Query in Machine Comprehension, IEEE ACCESS, 2018.10.4, 6:58702-58709.