Building Machine Learning System with Deep Neural Network for Text Processing

Singh, Shashi Pal; Kumar, Ajai; Darbari, Hemant; Rastogi, Anshika; Jain, Shikha; Joshi, Nisheeth

doi:10.1007/978-3-319-63645-0_56

Cited by 4 publications

(3 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gupta et al [43] showed the use of machine learning approached in developing NLP applications. Gupta et al [44] used fuzzy operations in analyzing sentiments of tweets on several topics. This approach showed very promising results over traditional approaches.…”

Section: Literature Reviewmentioning

confidence: 99%

Development of Part of Speech Tagger Using Deep Learning

Singh*¹,

Verma²,

Seal³

et al. 2019

IJEAT

View full text Add to dashboard Cite

Part of speech tagging is the initial step in development of NLP (natural language processing) application. POS Tagging is sequence labelling task in which we assign Part-of-speech to every word (Wi) which is sequence in sentence and tag (Ti) to corresponding word as label such as (Wi/Ti…. Wn/Tn). In this research project part of speech tagging is perform on Hindi. Hindi is the fourth most popular language and spoken by approximately 4billion people across the globe. Hindi is free word-order language and morphologically rich language due to this applying Part of Speech tagging is very challenging task. In this paper we have shown the development of POS tagging using neural approach.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Development of Part of Speech Tagger Using Deep Learning

Singh*¹,

Verma²,

Seal³

et al. 2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…Joshi et al [33] investigated some approaches to classifying documents and further suggested an approach for effective classification of text documents. Singh et al [34] developed an approach to automatically generate transfer grammar rules. This approach significantly improved the development process of their transfer-based MT engine.…”

Section: Literature Reviewmentioning

confidence: 99%

Development of English-Hindi Interactive Machine Translation

Sharma¹,

Seth²,

Syed³

et al. 2019

IJEAT

View full text Add to dashboard Cite

Machine Translation systems are still far from being perfect and to improve their performance the concept of Interactive Machine Translation (IMT) was introduced. This paper proposes an IMT system, which uses Statistical Machine Translation and a bilingual corpus on which several algorithms (Word error rate, Position Independent Error Rate, Translation Error Rate, n-grams) are implemented to translate text from English to Indian languages. The proposed system improves both the speed and productivity of the human translators as found through experiments.

show abstract

“…After the layer-wise feature learning, DNN can adaptively extract deep and essential features according to the internal structure of massive data without domain knowledge. DNN has been successfully applied in speech recognition [ 11 ], image classification [ 12 ], motion recognition [ 13 ], text processing [ 14 ] and many other domains. In the past few years, the typical deep learning frameworks including deep autoencoder (DAE), deep belief network (DBN), deep convolutional neural network (DCNN), deep recurrent neural network (DRNN) and their variants have been developed in the field of machine health monitoring [ 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

A Time-Distributed Spatiotemporal Feature Learning Method for Machine Health Monitoring with Multi-Sensor Time Series

Qiao

Wang

et al. 2018

Sensors

View full text Add to dashboard Cite

Data-driven methods with multi-sensor time series data are the most promising approaches for monitoring machine health. Extracting fault-sensitive features from multi-sensor time series is a daunting task for both traditional data-driven methods and current deep learning models. A novel hybrid end-to-end deep learning framework named Time-distributed ConvLSTM model (TDConvLSTM) is proposed in the paper for machine health monitoring, which works directly on raw multi-sensor time series. In TDConvLSTM, the normalized multi-sensor data is first segmented into a collection of subsequences by a sliding window along the temporal dimension. Time-distributed local feature extractors are simultaneously applied to each subsequence to extract local spatiotemporal features. Then a holistic ConvLSTM layer is designed to extract holistic spatiotemporal features between subsequences. At last, a fully-connected layer and a supervised learning layer are stacked on the top of the model to obtain the target. TDConvLSTM can extract spatiotemporal features on different time scales without any handcrafted feature engineering. The proposed model can achieve better performance in both time series classification tasks and regression prediction tasks than some state-of-the-art models, which has been verified in the gearbox fault diagnosis experiment and the tool wear prediction experiment.

show abstract

Building Machine Learning System with Deep Neural Network for Text Processing

Cited by 4 publications

References 1 publication

Development of Part of Speech Tagger Using Deep Learning

Development of Part of Speech Tagger Using Deep Learning

Development of English-Hindi Interactive Machine Translation

A Time-Distributed Spatiotemporal Feature Learning Method for Machine Health Monitoring with Multi-Sensor Time Series

Contact Info

Product

Resources

About