[1]陈文实,刘心惠,鲁明羽.基于编码解码器与深度主题特征抽取的多标签文本分类[J].南京师范大学学报(自然科学版),2019,42(04):61-68.[doi:10.3969/j.issn.1001-4616.2019.04.009]
　Chen Wenshi,Liu Xinhui,Lu Mingyu.Multi-label Text Classification Based on Seq2Seq Modeland Deep Topic Feature Extraction[J].Journal of Nanjing Normal University(Natural Science Edition),2019,42(04):61-68.[doi:10.3969/j.issn.1001-4616.2019.04.009]
点击复制

基于编码解码器与深度主题特征抽取的多标签文本分类()
分享到：

《南京师范大学学报》（自然科学版）[ISSN:1001-4616/CN:32-1239/N]

卷:
第42卷
期数:
2019年04期
页码:
61-68
栏目:
·数学与计算机科学·
出版日期:
2019-12-30

文章信息/Info

Title:
Multi-label Text Classification Based on Seq2Seq Modeland Deep Topic Feature Extraction
文章编号:
1001-4616(2019)04-0061-08
作者:
陈文实; 刘心惠; 鲁明羽
大连海事大学信息科学技术学院,辽宁 大连 116026
Author(s):
Chen Wenshi; Liu Xinhui; Lu Mingyu
School of Information Science and Technology,Dalian Maritime University,Dalian 116026,China
关键词:
多标签文本分类; 深度主题特征; 标签相关性; 编码解码器; attention机制
Keywords:
multi-label text classification; deep topic feature extraction; label correlation; seq2seq; attention mechanism
分类号:
TP311
DOI:
10.3969/j.issn.1001-4616.2019.04.009
文献标志码:
A
摘要:
本文提出了一种基于编码解码器与深度主题特征的模型,实现了多标签文本分类. 针对传统多标签文本分类方法的特征语义缺失的问题,采用一种长短时记忆(long short-term memory,LSTM)网络提取文本的局部特征与主题模型(latent dirichlet allocation,LDA)提取文本的全局特征的深度主题特征提取模型(deep topic feature extraction model,DTFEM),得到具有文本深层语义特征的语义编码向量,并将该编码向量作为解码器网络的输入. 解码器网
Abstract:
In this paper,a model based on seq2seq model and deep topic feature extraction is proposed to realize multi-label text classification. Aiming at the problem of feature semantics loss in traditional multi-label text classification method,a model is proposed to extract the local features of texts by using the Long Short-term Memory(LSTM)network and extract the global features of texts by using topic model(Latent Dirichlet Allocation,LDA)named Deep Topic Feature Extraction Model(DTFEM),and then obtain the semantic coding vector with deep semantic feature,and the vector is used as the input of the decoder network. The decoder network regards the task of multi-label text classification as the process of sequence generation,solves the problem of label correlation of multi-label text classification,and adds the attention mechanism to calculate the probability distribution of attention,highlights the effect of key input on the output,improves the semantic missing problem due to excessive input,and realizes the final multi-label text classification. The experimental results show that the model can obtain better results than the traditional multi-label text classification system. In addition,the experiments have shown that the use of deep topic features can improve the performance of multi-label text classification.

参考文献/References:

[1] GONG Y,KE Q,ISARD M,et al. A multi-view embedding space for modeling internet images,tags and their semantics[J]. International journal of computer vision,2014,106(2):210-233.
[2]PORIA S,CAMBRIA E,BAJPAI R,et al. A review of affective computing:from unimodal analysis to multimodal fusion[J]. Information fusion,2017,37:98-125.
[3]CAMBRIA E. Affective computing and sentiment analysis[J]. IEEE intelligent systems,2016,31(2):102-107.
[4]CARRERAS X,MARQUEZ L. Boosting trees for anti-spam email filtering[C]//Proceeding of the 4th International Conference on Recent Advances in Natural Language Processing. Tzigov Chark,Bulgaria,2001.
[5]BLEI D M,NG A Y,JORDAN M I. Latent dirichlet allocation[J]. Journal of machine learning research,2003,3:993-1022.
[6]黄泽明. 基于主题模型的学术论文推荐系统研究[D]. 大连:大连海事大学,2013.
[7]王李冬,魏宝刚,袁杰. 基于概率主题模型的文档聚类[J]. 电子学报,2012,40(11):2346-2350.
[8]邱云飞,郭弥纶,邵良杉. 基于主题树的微博突发话题检测[J]. 计算机应用,2014,34(8):2332-2335.
[9]HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural computation,1997,9(8):1735-1780.
[10]SUTSKEVER I,VINYALS O,LE Q V. Sequence to sequence learning with neural networks[C]//Proceedings of the 27th International Conference on Neural Information Processing systems. Montreal,Canada,2014.
[11]CHO K,VAN MERRI?NBOER B,GULCEHRE C,et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha,Qatar,2014.
[12]VINYALS O,LE Q. A neural conversational model[J]. arXiv preprint arXiv:1506.05869,2015.
[13]RUSH A M,CHOPRA S,WESTON J. A neural attention model for abstractive sentence summarization[J]. arXiv preprint arXiv:1509.00685,2015.
[14]LUONG M T,LE Q V,SUTSKEVER I,et al. Multi-task sequence to sequence learning[C]//Proceedings of ICLR. San Juan,Puerto Rico,2015.
[15]BAHDANAU D,CHO K,BENGIO Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv:1409.0473,2014.
[16]ZHANG M L,ZHOU Z H. A review on multi-label learning algorithms[J]. IEEE transactions on knowledge and data engineering,2014,26(8):1819-1837.
[17]LUACES R ó,DíEZ P J,BARRANQUERO T J,et al. Binary relevance efficacy for multilabel classification[J]. Progress in artificial intelligence,2012,1(4):303-313.
[18]CHERMAN E A,MONARD M C,METZ J. Multi-label problem transformation methods:a case study[J]. CLEI electronic journal,2011,14(1):4-4.
[19]READ J,PFAHRINGER B,HOLMES G,et al. Classifier chains for multi-label classification[J]. Machine learning,2011,85(3):333.
[20]ZHANG M L,ZHOU Z H. ML-KNN:A lazy learning approach to multi-label learning[J]. Pattern recognition,2007,40(7):2038-2048.
[21]ELISSEEFF A,WESTON J. A kernel method for multi-labelled classification[C]//Proceedings of the 14th International Conference on Neural Information Proceesing Systems:Natural and Synthetic. Vancouver,British Columbia,Canada,2001.
[22]XU K,BA J,KIROS R,et al. Show,attend and tell:Neural image caption generation with visual attention[C]//Proceedings of the 32nd International Conference on Machine Learning. Lille,France,2015.
[23]LEE C Y,OSINDERO S. Recursive recurrent nets with attention modeling for ocr in the wild[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las vegas,2016.

备注/Memo

备注/Memo:
收稿日期:2019-06-25.
基金项目:国家自然科学基金(61073133).
通讯联系人:鲁明羽,博士,教授,博士生导师,研究方向:自然语言处理. E-mail:lumingyu@dlmu.edu.cn
更新日期/Last Update: 2019-12-31