Chinese Relation Extraction Based on Deep Belief Nets

Abstract

Relation extraction is a fundamental task in information extraction, which is to identify the semantic relationships between two entities in the text. In this paper, deep belief nets (DBN), which is a classifier of a combination of several unsupervised learning networks, named RBM (restricted Boltzmann machine) and a supervised learning network named BP (back-propagation), is presented to detect and classify the relationships among Chinese name entities. The RBM layers maintain as much information as possible when feature vectors are transferred to next layer. The BP layer is trained to classify the features generated by the last RBM layer. The experiments are conducted on the Automatic Content Extraction 2004 dataset. This paper proves that a character-based feature is more suitable for Chinese relation extraction than a word-based feature. In addition, the paper also performs a set of experiments to assess the Chinese relation extraction on different assumptions of an entity categorization feature. These experiments showed the comparison among models with correct entity types and imperfect entity type classified by DBN and without entity type. The results show that DBN is a successful approach in the high-dimensional-feature-space information extraction task. It outperforms state-of-the-art learning models such as SVM and back-propagation networks.

Academic Activities Transaction Extraction Based on Deep Belief Network

“…The concept of deep learning was first proposed by Professor Hinton in 2006 [11]. Deep learning method has achieved good results in image recognition and speech recognition [12][13][14].…”

“…The DBN model constructed an energy function and used the hidden layer structure of the RBM to learn the text advanced features. In 2014, Chen used the DBN model and achieved the best effect in the contrast experiment of ACE2004 corpus entity recognition with CRF, SVM, and BP [17]. In 2016, Feng et al used the word vector as the input of the DBN and achieved 89.58% value in entity recognition of people's daily corpus [18].…”

“…It is a depth learning model that contains multilayer RBM layer and a BP layer. The model has autonomic learning advanced feature from shallow feature of text and has powerful classification ability for high dimensional sparse feature vectors [11].…”

Sentiment analysis for Chinese microblog based on deep neural networks with convolutional extension features

“…The emotion polarity of bloggers might reflect his or her hobbies and interests [1][2][3][4]. Microblog sentiment classification emerges as a challenging task [5][6][7][8]. The general realization of emotion polarity detection commonly includes extraction of features [9][10][11] and selection of machine learning methods [12][13][14][15].…”

“…Xavier Glorot [10] proposes a deep learning approach which shows linear classifiers trained with higher-level learned feature representation of reviews outperforming traditional surface learning methods. Deselaers [11] and Chen [5] testify the validity of deep learning on NLP tasks. The deep learning model is showing its abilities of learning deep structure knowledge such as semantic information embedded in text, so deep learning models could solve classification problem with relatively better performance than surface learning models.…”