Chinese Event Extraction Based on Feature Weighting

Fu, Jianfeng; Liu, Zongtian; Zhong, Zhang; Shan, Jianfang

doi:10.3923/itj.2010.184.187

Cited by 13 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fu [10] proposed an algorithm of event factor identification based on feature weighting. This algorithm firstly improves the Relief feature selection algorithm in the classification algorithm and then applies it to the clustering algorithm.…”

Section: Machine Learningmentioning

confidence: 99%

Chinese Event Extraction Based on Attention and Semantic Features: A Bidirectional Circular Neural Network

Zhang

2018

Future Internet

View full text Add to dashboard Cite

Chinese event extraction uses word embedding to capture similarity, but suffers when handling previously unseen or rare words. From the test, we know that characters may provide some information that we cannot obtain in words, so we propose a novel architecture for combining word representations: character–word embedding based on attention and semantic features. By using an attention mechanism, our method is able to dynamically decide how much information to use from word or character level embedding. With the semantic feature, we can obtain some more information about a word from the sentence. We evaluate different methods on the CEC Corpus, and this method is found to improve performance.

show abstract

Section: Machine Learningmentioning

confidence: 99%

Chinese Event Extraction Based on Attention and Semantic Features: A Bidirectional Circular Neural Network

Zhang

2018

Future Internet

View full text Add to dashboard Cite

show abstract

“…Displacement control of hoisting point: each hoisting point is equipped with the displacement sensor, and detects absolute height of the hoisting point. After each travel is complete, correct travel value of the oil cylinder according to absolute height of the hoisting point; set alert value of absolute height difference, monitor absolute height difference of each hoisting point during lifting process, and stop hoisting if it reaches alert value [2].…”

Section: ) Force Controlmentioning

confidence: 99%

Synchronous Control Technology Research of Hydraulic Lifting System

Wen²,

Mei

2012

AMM

View full text Add to dashboard Cite

In conventional “flow control valve and travel switch” control strategy, relative height difference between multiple cylinders only reach accuracy of centimetre grade, which can’t meet synchronous control accuracy requirements of many engineering. In order to improve multiple cylinders synchronous accuracy of the hydraulic lifting system, this paper takes a hydraulic lifting system as basis, which studies PID closed loop control system using electro-hydraulic proportional valve and high-precision displacement accuracy sensor, and the synchronous accuracy of 4 cylinders hydraulic lifting system is improved to millimetre grade.

show abstract

“…In 2002, Chieu and Ng introduced a maximum entropy classifier [ 29 ] and applied it for the purpose of recognizing events and their elements. For addressing the problem that existing event recognition methods did not consider context, Fu et al proposed an event extraction method based on weight features of event elements in the event ontology [ 30 ]. In 2006, Ahn [ 31 ] proposed a method to recognize event classes and elements.…”

Section: Introductionmentioning

confidence: 99%

Event Recognition Based on Deep Learning in Chinese Texts

2016

Self Cite

View full text Add to dashboard Cite

Event recognition is the most fundamental and critical task in event-based natural language processing systems. Existing event recognition methods based on rules and shallow neural networks have certain limitations. For example, extracting features using methods based on rules is difficult; methods based on shallow neural networks converge too quickly to a local minimum, resulting in low recognition precision. To address these problems, we propose the Chinese emergency event recognition model based on deep learning (CEERM). Firstly, we use a word segmentation system to segment sentences. According to event elements labeled in the CEC 2.0 corpus, we classify words into five categories: trigger words, participants, objects, time and location. Each word is vectorized according to the following six feature layers: part of speech, dependency grammar, length, location, distance between trigger word and core word and trigger word frequency. We obtain deep semantic features of words by training a feature vector set using a deep belief network (DBN), then analyze those features in order to identify trigger words by means of a back propagation neural network. Extensive testing shows that the CEERM achieves excellent recognition performance, with a maximum F-measure value of 85.17%. Moreover, we propose the dynamic-supervised DBN, which adds supervised fine-tuning to a restricted Boltzmann machine layer by monitoring its training performance. Test analysis reveals that the new DBN improves recognition performance and effectively controls the training time. Although the F-measure increases to 88.11%, the training time increases by only 25.35%.

show abstract

Chinese Event Extraction Based on Feature Weighting

Cited by 13 publications

References 4 publications

Chinese Event Extraction Based on Attention and Semantic Features: A Bidirectional Circular Neural Network

Chinese Event Extraction Based on Attention and Semantic Features: A Bidirectional Circular Neural Network

Synchronous Control Technology Research of Hydraulic Lifting System

Event Recognition Based on Deep Learning in Chinese Texts

Contact Info

Product

Resources

About