基于语义结构的迁移学习文本特征对齐算法

doi:10.19678/j.issn.1000-3428.0050574

计算机工程 ›› 2019, Vol. 45 ›› Issue (5): 116-121. doi: 10.19678/j.issn.1000-3428.0050574

基于语义结构的迁移学习文本特征对齐算法

卢晨阳,康雁,杨成荣,蒲斌

云南大学软件学院,昆明 650500

收稿日期:2018-03-02 出版日期:2019-05-15 发布日期:2019-05-15
作者简介:卢晨阳(1994—),男,硕士研究生,主研方向为自然语言处理;康雁,副教授;杨成荣、蒲斌,硕士研究生。
基金资助:
国家自然科学基金(61762092);云南省软件工程重点实验室开放基金(2017SE204)。

Text Feature Alignment Algorithm for Transfer Learning Based on Semantic Structure

LU Chenyang,KANG Yan,YANG Chengrong,PU Bin

School of Software,Yunnan University,Kunming 650500,China

Received:2018-03-02 Online:2019-05-15 Published:2019-05-15

摘要/Abstract

摘要：

特征对齐在源域和目标域空间不一致时会导致负迁移现象。为此,提出一种基于GloVe和WordNet模型的迁移学习文本特征对齐算法。根据数据样本词性和类别对分类任务进行特征筛选,选择源域和目标域的领域共有词作为枢纽词,使用GloVe模型对齐源域和目标域中最相似的非枢纽特征。在此基础上,根据源域和目标域的非共有特征,通过WordNet模型对领域独立特征完成强语义对齐,同时利用含有枢纽特征的对齐三元组表示对齐特征。实验结果表明,该算法可有效降低特征维度,扩充特征空间,提高跨领域文本分类精度。

关键词: 迁移学习, 特征对齐, 词向量, 词网, 文本挖掘

Abstract:

Feature alignment causes a negative transfer when the source domain space and target domain space are inconsistent.Therefore,a text feature alignment algorithm for transfer learning based on the GloVe and WordNet model is proposed.According to the part of speech and category of the sample data,feature filtering is performed to classification tasks.The shared terms of the source domains and target domain are selected as pivot words,and the GloVe model is used to align the most similar non-pivot features in the source domain and target domain.On this basis,according to the unique features of the source domain and target domain,strong semantic alignment is achieved through the WordNet model for the domain independent features.At the same time,alignment features are represented by aligning triples with pivot features.Experimental results show that the algorithm can effectively reduce the feature dimension,expand the feature space,and improve the accuracy of cross-domain text classification.

Key words: transfer learning, feature alignment, word vector, WordNet, text mining

中图分类号:

TP391

卢晨阳,康雁,杨成荣,蒲斌. 基于语义结构的迁移学习文本特征对齐算法[J]. 计算机工程, 2019, 45(5): 116-121.

LU Chenyang,KANG Yan,YANG Chengrong,PU Bin. Text Feature Alignment Algorithm for Transfer Learning Based on Semantic Structure[J]. Computer Engineering, 2019, 45(5): 116-121.

https://www.ecice06.com/CN/Y2019/V45/I5/116

参考文献

［1］LIU Bing.Sentiment analysis and opinion mining［EB/OL］.［2018-01-16］.https://www.cs.uic.edu/~liub/FBS/SentimentAnalysis-and-OpinionMining.html.
［2］LIU Bing.Web data mining［M］.Berlin,Germany:Springer,2011.
［3］PANG Bo,LEE L.Thumbs up? sentiment classification using machine learning［EB/OL］.［2018-01-16］.https://arxiv.org/pdf/cs/0205070.pdf.
［4］BLITZER J,MCDONALD R,PEREIRA F.Domain adaptation with structural correspondence learning［C］//Proceedings of Conference on Empirical Methods in Natural Language Processing.Stroudsburg,USA:Association for Computational Linguistics,2006:120-128.
［5］PAN Jialin,NI Xiaochuan,SUN Jiantao,et al.Cross-domain sentiment classification via spectral feature alignment［C］//Proceedings of the 19th International Conference on World Wide Web.New York,USA:ACM Press,2010:751-760.
［6］ZHANG Shaowu,LIU Huali,YANG Liang,et al.A cross-domain sentiment classification method based on extraction of key sentiment sentence［J］.Natural Language Processing and Chinese Computing,2015,9362:90-101.
［7］孟佳娜,段晓东,杨亮.基于特征变换的跨领域产品评论倾向性分析［J］.计算机工程,2013,39(10):167-171.
［8］BOLLEGALA D,WEIR D,CARROLL J.Cross-domain sentiment classification using a sentiment sensitive thesaurus［J］.IEEE Transactions on Knowledge and Data Engineering,2013,25(8):1719-1731.
［9］XIA Rui,ZONG Chengqing,HU Xuelei,et al.Feature ensemble plus sample selection:domain adaptation for sentiment classification［J］.IEEE Intelligent Systems,2013,28(3):10-18.
［10］ZHOU Guangyou,HE Tingting,WU Wensheng,et al.Linking heterogeneous input features with pivots for domain adaptation［C］//Proceedings of the 24th International Conference on Artificial Intelligence.［S.l.］:AAAI Press,2015:1419-1425.
［11］魏晓聪,林鸿飞.面向迁移学习的文本特征对齐算法［J］.计算机工程,2017,43(2):215-219.
［12］ZHANG Yuhong,XU Xu,HU Xuegang.A common subspace construction method in cross-domain sentiment classification［C］//Proceedings of International Conference on Electronic Science and Automation Control.［S.l.］:Atlantis Press,2015:48-52.
［13］ZHOU Guangyou,ZHOU Yin,GUO Xiyue,et al.Cross-domain sentiment classification via topical correspondence transfer［J］.Neurocomputing,2015,159:298-305.
［14］GLOROT X,BORDES A,BENGIO Y.Domain adapta-tion for large-scale sentiment classification:a deep learning approach［C］//Proceedings of the 28th International Conference on Machine Learning.［S.l.］:Omnipress,2011:513-520.
［15］BENGIO Y,GUYON G,DROR V,et al.Deep learning of representations for unsupervised and transfer learning［EB/OL］.［2018-01-16］.https://www.docin.com/p-1690924284.html.
［16］COLLOBERT R,WESTON J.A unified architecture for natural language processing:deep neural networks with multitask learning［C］//Proceedings of the 25th Inter-national Conference on Machine learning.New York,USA:ACM Press,2008:160-167.
［17］MARQUEZ L,RODRGUEZ H.Part-of-speech tagging using decision trees［C］//Proceedings of the 10th European Conference on Machine Learning.London,UK:Springer,1998:25-36.
［18］LANDAUER T K,DUMAIS S T.A solution to plato’s problem:the latent semantic analysis theory of acquisition,induction,and representation of knowledge［J］.Psychological Review,1997,104(2):211-240.
［19］MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space［EB/OL］.［2018-01-16］.https://arxiv.org/pdf/1301.3781.pdf.
［20］PENNINGTON J,SOCHER R,MANNING C.GloVe:global vectors for word representation［EB/OL］.［2018-01-16］.https://nlp.stanford.edu/projects/glove/.
［21］MILLER G A.WordNet:a lexical database for English［J］.Communications of the Association for Computing Machinery,1995,38(11):39-41.

[1]	王晋涛, 秦昂, 张元, 陈一飞, 王廷凤, 谢承霖, 邹刚. 基于注意力增强与特征融合的中文医学实体识别[J]. 计算机工程, 2024, 50(7): 324-332.
[2]	李致金, 汤佳辉, 闫金凤. 基于边缘计算的轻量化识别方法[J]. 计算机工程, 2024, 50(6): 287-295.
[3]	焦世超, 关日鹏, 况立群, 熊风光, 韩燮. 深度语义关联学习的基于图像视觉数据跨域检索[J]. 计算机工程, 2024, 50(5): 190-199.
[4]	包善书, 车波, 邓林红. 基于双源域迁移学习的肺音信号识别[J]. 计算机工程, 2023, 49(9): 295-302, 312.
[5]	王爱玲, 马文臻, 邹自明, 钟佳. 基于领域自适应的卫星工程参数异常检测[J]. 计算机工程, 2023, 49(5): 29-37,47.
[6]	白俊卿, 韩柏迅, 张丰侠. 基于深度学习的无人机图像语义分割算法研究[J]. 计算机工程, 2023, 49(4): 233-239.
[7]	郑云涛, 叶家炜. 基于茫然传输协议的FATE联邦迁移学习方案[J]. 计算机工程, 2023, 49(2): 24-30.
[8]	张欢, 黄涛, 许俊杰, 徐川, 杨威. 多层渐进式特征对齐网络优化的空地影像稳健匹配[J]. 计算机工程, 2023, 49(10): 178-185.
[9]	伍洲, 杨寒石, 邬俊俊, 张海军, 宋晴. 进化迁移优化算法综述[J]. 计算机工程, 2023, 49(1): 1-14.
[10]	邱鸿辉, 刘海林, 陈磊. 基于协方差矩阵调整的多目标多任务优化算法[J]. 计算机工程, 2022, 48(8): 306-312.
[11]	李军怀, 陈苗苗, 王怀军, 崔颖安, 张爱华. 基于ALBERT-BGRU-CRF的中文命名实体识别方法[J]. 计算机工程, 2022, 48(6): 89-94,106.
[12]	李冉冉, 刘大明, 刘正, 常高祥. 融合笔画特征的胶囊网络文本分类[J]. 计算机工程, 2022, 48(3): 69-73,80.
[13]	雷恒林, 古兰拜尔·吐尔洪, 买日旦·吾守尔, 曾琪. 基于Hellinger距离与词向量的终身机器学习主题模型[J]. 计算机工程, 2022, 48(11): 89-95.
[14]	王丽娟, 张霖, 尹明, 郝志峰, 蔡瑞初, 温雯. 基于正交基的多视图迁移谱聚类[J]. 计算机工程, 2022, 48(10): 37-44,54.
[15]	梁正友, 刘德志, 孙宇. 结合迁移学习与可分离三维卷积的微表情识别方法[J]. 计算机工程, 2022, 48(1): 228-235.

选择文件类型/文献管理软件名称

选择包含的内容

基于语义结构的迁移学习文本特征对齐算法

Text Feature Alignment Algorithm for Transfer Learning Based on Semantic Structure

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于语义结构的迁移学习文本特征对齐算法

Text Feature Alignment Algorithm for Transfer Learning Based on Semantic Structure

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价