混合特征及多头注意力的中文短文本分类

doi:10.3778/j.issn.1002-8331.2302-0396

摘要/Abstract

摘要： 传统的短文本分类研究方法存在两方面不足，一是不能全面地表示文本的语义信息，二是无法充分地提取和融合文本全局和局部信息。基于此，提出一种混合特征及多头注意力（HF-MHA）的中文短文本分类方法。该方法利用预训练模型计算中文短文本的字符级向量和词级向量表示，以得到更全面的文本特征向量表示；采用多头注意力机制捕捉文本序列中的依赖关系，以提高文本的语义理解；通过卷积神经网络分别提取两种向量表示的特征，并将其融合为一个特征向量，以整合文本的全局和局部信息；通过输出层得到分类结果。在三个公开数据集上的实验表明，HF-MHA能够有效地提升中文短文本分类的性能。

关键词: 中文短文本分类, 注意力机制, 词级向量, 字符级向量

Abstract: Traditional short text classification methods have two shortcomings：they cannot fully represent the semantic information of the text, and they cannot effectively extract and integrate the global and local information of the text. Based on this, a Chinese short text classification with hybrid features and multi-head attention (HF-MHA) is proposed. The method uses a pre-trained model to calculate the character-level and word-level vector representations of Chinese short texts, to obtain a more comprehensive text feature vector representation. Then it adopts a multi-head attention mechanism to capture the dependency relationships in the text sequence, to improve the semantic understanding of the text. It uses a convolutional neural network to extract the features of the two vector representations separately, and integrates them into a feature vector, to integrate the global and local information of the text. Finally, it obtains the classification result through the output layer. Experiments on three public datasets show that HF-MHA can effectively improve the performance of Chinese short text classification.

Key words: Chinese short text classification, attention mechanism, word-level vector, character-level vector

江结林, 朱永伟, 许小龙, 崔燕, 赵英男. 混合特征及多头注意力的中文短文本分类[J]. 计算机工程与应用, 2024, 60(9): 237-243.

JIANG Jielin, ZHU Yongwei, XU Xiaolong, CUI Yan, ZHAO Yingnan. Chinese Short Text Classification with Hybrid Features and Multi-Head Attention[J]. Computer Engineering and Applications, 2024, 60(9): 237-243.

参考文献

[1] 李博涵, 向宇轩, 封顶, 等. 融合知识感知与双重注意力的短文本分类模型[J]. 软件学报, 2022, 33(10): 3565-3581.
LI B H, XIANG Y X, FENG D, et al. Short text classification model combining knowledge aware and dual attention[J]. Journal of Software, 2022, 33(10): 3565-3581.
[2] 淦亚婷, 安建业, 徐雪. 基于深度学习的短文本分类方法研究综述[J]. 计算机工程与应用, 2023, 59(4): 43-53.
GAN Y T, AN J Y, XU X. Survey of short text classification methods based on deep learning[J]. Computer Engineering and Applications, 2023, 59(4): 43-53.
[3] 郑诚, 陈杰, 董春阳. 结合图卷积的深层神经网络用于文本分类[J]. 计算机工程与应用, 2022, 58(7): 206-212.
ZHENG C, CHEN J, DONG C Y. Deep neural network combined with graph convolution for text classification[J]. Computer Engineering and Applications, 2022, 58(7): 206-212.
[4] CONNEAU A, SCHWENK H, BARRAULT L, et al. Very deep convolutional networks for text classification[J]. arXiv:1606.01781, 2016.
[5] TAI K S, SOCHER R, MANNING C D. Improved semantic representations from tree-structured long short-term memory networks[J]. arXiv:1503.00075, 2015.
[6] ZENG D, LIU K, LAI S, et al. Relation classification via convolutional deep neural network[C]//Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, 2014: 2335-2344.
[7] BOLLEGALA D, ATANASOV V, MAEHARA T, et al. ClassiNet-predicting missing features for short-text classification[J]. ACM Transactions on Knowledge Discovery from Data (TKDD), 2018, 12(5): 1-29.
[8] LEE J, CHO K, HOFMANN T. Fully character-level neural machine translation without explicit segmentation[J]. Transactions of the Association for Computational Linguistics, 2017, 5: 365-378.
[9] LAI Y, FENG Y, YU X, et al. Lattice CNNs for matching based Chinese question answering[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 6634-6641.
[10] 肖琳, 陈博理, 黄鑫, 等. 基于标签语义注意力的多标签文本分类[J]. 软件学报, 2020, 31(4): 1079-1089.
XIAO L, CHEN B L, HUANG X, et al. Multi-label text classification method based on label semantic information[J]. Journal of Software, 2020, 31(4): 1079-1089.
[11] TAO H, TONG S, ZHAO H, et al. A radical-aware attention-based model for chinese text classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 5125-5132.
[12] HAO M, XU B, LIANG J Y, et al. Chinese short text classification with mutual-attention convolutional neural networks[J]. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 2020, 19(5): 1-13.
[13] YU C T, SALTON G. Precision weighting—an effective automatic indexing method[J]. Journal of the ACM (JACM), 1976, 23(1): 76-88.
[14] BIJALWAN V, KUMAR V, KUMARI P, et al. KNN based machine learning approach for text and document mining[J]. International Journal of Database Theory and Application, 2014, 7(1): 61-70.
[15] GOUDJIL M, KOUDIL M, BEDDA M, et al. A novel active learning method using SVM for text classification[J]. International Journal of Automation and Computing, 2018, 15(3): 290-298.
[16] KIM Y. Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 2014: 1746-1751.
[17] LIU J, CHANG W C, WU Y, et al. Deep learning for extreme multi-label text classification[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017: 115-124.
[18] JOHNSON R, ZHANG T. Deep pyramid convolutional neural networks for text categorization[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, 2017: 562-570.
[19] SHEN T, ZHOU T, LONG G, et al. Disan: directional self-attention network for RNN/CNN-free language understanding[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018: 5446-5455.
[20] JANG B, KIM M, HARERIMANA G, et al. Bi-LSTM model to increase accuracy in text classification: combining Word2vec CNN and attention mechanism[J]. Applied Sciences, 2020, 10(17): 5841.
[21] ZHANG Y, ZHENG J, JIANG Y, et al. A text sentiment classification modeling method based on coordinated CNN‐LSTM-
attention model[J]. Chinese Journal of Electronics, 2019, 28(1): 120-126.
[22] LIU Z, HUANG H, LU C, et al. Multichannel CNN with attention for text classification[J]. arXiv:2006.16174, 2020.
[23] MIKOLOV T, CHEN K, CORRADO G, et al. Efficient estimation of word representations in vector space[J]. arXiv:1301.3781, 2013.
[24] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[C]//Advances in Neural Information Processing Systems, 2013: 3111-3119.
[25] DEVLIN J, CHANG M W, LEE K, et al. Bert: pre-training of deep bidirectional transformers for language understanding[J]. arXiv:1810.04805, 2018.
[26] ZHANG Z, HAN X, LIU Z, et al. ERNIE: enhanced language representation with informative entities[J]. arXiv:1905.
07129, 2019.
[27] SUN Y, WANG S, LI Y, et al. Ernie 2.0: a continual pre-training framework for language understanding[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 8968-8975.
[28] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017: 5998-6008.
[29] LI Y, ZHANG Y, ZHAO Z, et al. CSL: a large-scale Chinese scientific literature dataset[J]. arXiv:2209.05034, 2022.
[30] LIU P, QIU X, HUANG X. Recurrent neural network for text classification with multi-task learning[J]. arXiv:1605.05101, 2016.
[31] LAI S, XU L, LIU K, et al. Recurrent convolutional neural networks for text classification[C]//Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015: 2267-2273.
[32] SUN Y, WANG S, FENG S, et al. Ernie 3.0: large-scale knowledge enhanced pre-training for language understanding and generation[J]. arXiv:2107.02137, 2021.