Change language

Deep learning for natural language processing


Deep learning for natural language processing Karthiek Bokka, Shubhangi Hora, Tanuj Jain, Monicah Wambugu

Applying deep learning approaches to various NLP tasks can take your computational algorithms to a whole new level in terms of speed and accuracy.

Deep learning for natural language processing PDF download

Deep learning for natural language processing begins by highlighting the fundamental building blocks of the natural language processing domain. The book then presents the problems you can solve using state-of-the-art neural network models. After that, diving into the different neural network architectures and their specific application areas will help you understand how to choose the best model for your needs. As you work through this deep learning book, you will explore convolutional, recurrent, and recursive neural networks, in addition to long short-term memory networks (LSTM). Understanding these networks will help you implement their models with Keras. In later chapters, you will be able to develop a trigger word recognition application using NLP techniques such as the attention model and ray search.

What you will learn

  • Understand various pre-processing techniques for deep learning problems
  • Build a vector representation of text using word2vec and GloVe
  • Create a named entity recognizer and parts-of-speech tagger with Apache OpenNLP
  • Build a machine translation model in Keras
  • Develop a text generation application using LSTM
  • Build a trigger word detection application using an attention model

About the authors

Karthiek Reddy Bokka is a voice and audio machine learning engineer who graduated from the University of Southern California and currently works for Biamp Systems in Portland. His interests include Deep Learning, Digital Signal and Audio Processing, Natural Language Processing, Computer Vision. He has experience in designing, building and deploying artificial intelligence applications to solve real world problems with various forms of practical data, including images, speech, music, unstructured raw data etc.

Tanuj Jain is a data scientist working at a company based in Germany. He holds a master's degree in electrical engineering with a specialization in statistical pattern recognition. He has developed deep learning models and put them into production for commercial use in his current work. Natural language processing is a particular area of ​​interest for him and he has applied his know-how to the tasks of classification and sentiment evaluation.

Monicah Wambugu is the Principal Data Scientist at Loanbee, a fintech company that provides micro-loans by leveraging data, machine learning and analytics to perform alternative credit scoring. She is a graduate student in the School of Information at UC Berkeley Masters in Information Management and Systems. Monicah is particularly interested in how data science and machine learning can be used to design products and applications that meet the behavioral and socio-economic needs of target audiences.

Shubhangi Hora is a Python developer, artificial intelligence enthusiast and writer. With a background in Computer Science and Psychology, she is particularly interested in AI related to mental health. Shubhangi is based in Pune, India and is passionate about promoting natural language processing through machine learning and deep learning. Aside from that, she likes the performing arts and is a trained musician.

See also

Learn programming in R: courses


Best Python online courses for 2022


Best laptop for Fortnite


Best laptop for Excel