Distant Supervision for Relation Extraction via Sparse Representation

被引:0
作者
Zeng, Daojian [1 ]
Lai, Siwei [1 ]
Wang, Xuepeng [1 ]
Liu, Kang [1 ]
Zhao, Jun [1 ]
Lv, Xueqiang [2 ]
机构
[1] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100864, Peoples R China
[2] Beijing Informat Sci & Technol Univ, Beijing Key Lab Internet Culture & Digital Dissem, Beijing, Peoples R China
来源
CHINESE COMPUTATIONAL LINGUISTICS AND NATURAL LANGUAGE PROCESSING BASED ON NATURALLY ANNOTATED BIG DATA, CCL 2014 | 2014年 / 8801卷
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In relation extraction, distant supervision is proposed to automatically generate a large amount of labeled data. Distant supervision heuristically aligns the given knowledge base to free text and consider the alignment as labeled data. This procedure is effective to get training data. However, this heuristically label procedure is confronted with wrong labels. Thus, the extracted features are noisy and cause poor extraction performance. In this paper, we exploit the sparse representation to address the noise feature problem. Given a new test feature vector, we first compute its sparse linear combination of all the training features. To reduce the influence of noise features, a noise term is adopted in the procedure of finding the sparse solution. Then, the residuals to each class are computed. Finally, we classify the test sample by assigning it to the object class that has minimal residual. Experimental results demonstrate that the noise term is effective to noise features and our approach significantly outperforms the state-of-the-art methods.
引用
收藏
页码:151 / 162
页数:12
相关论文
共 22 条
[1]  
[Anonymous], P IJCNLP
[2]  
[Anonymous], 2006, P 12 ACM SIGKDD INT, DOI DOI 10.1145/1150402.1150492
[3]  
Aviyente S., 2006, ADV NEURAL INFORM PR, P609, DOI DOI 10.7551/MITPRESS/7503.001.0001
[4]  
Bunescu Razvan C, 2005, Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing, P724
[5]  
Chen SSB, 2001, SIAM REV, V43, P129, DOI [10.1137/S003614450037906X, 10.1137/S1064827596304010]
[6]   For most large underdetermined systems of linear equations the minimal l1-norm solution is also the sparsest solution [J].
Donoho, DL .
COMMUNICATIONS ON PURE AND APPLIED MATHEMATICS, 2006, 59 (06) :797-829
[7]  
GuoDong Z, 2005, P 43 ANN M ASS COMP, P427, DOI [DOI 10.3115/1219840.1219893, 10.3115/1219840.1219893]
[8]   DISTRIBUTIONAL STRUCTURE [J].
Harris, Zellig S. .
WORD-JOURNAL OF THE INTERNATIONAL LINGUISTIC ASSOCIATION, 1954, 10 (2-3) :146-162
[9]  
Hasegawa T., 2004, P 42 ANN M ASS COMP, DOI [10.3115/1218955.1219008, DOI 10.3115/1218955.1219008]
[10]  
Hoffmann R., 2011, KNOWLEDGE BASED WEAK, P541