Interest in Neural networks is growing with many areas from image recognition to speech processing reporting impressive results. Applications in Natural language processing with Neural networks have found multiple applications. With advances in software and hardware technologies, and interest in AI based applications growing, it is time to understand neural networks applied to natural language processing better!
In this workshop, we will discuss the basics of neural networks and natural language processing and discuss how neural approaches differ from traditional natural language modelling techniques with practical applications.All participants will get a trial access to QuSandbox
What you will learn
- Key NLP techniques
- Key Neural Network models and techniques
- How do you choose an algorithm for a specific goal?
- Text tokenization, word embeddings (word2vec, Glove).
- Deep Neural techniques and using RNNs and Encoder-Decoder networks for text processing.
- Encoder-Decoder Seq2Seq, Seq2Vec models
- Practical Case studies with fully functional code
Basics of NLP
- Natural Language Processing Basics
- Key challenges when processing text
- Syntax and Semantics
- Text pre-processing: Tokenization, Lemmatization, Stemming
- Language Modeling
- N-Grams, Bag-of-words, Word embeddings; Word2vec, Glove
- Case study 1: Working with Edgar data in Python
- Introduction to Deep Neural Networks
- Introduction to Keras and Tensorflow
- MLPs, CNNs, RNNs, Encoder Decoders
- Deep Learning techniques
- CBuilding a Deep Neural Network with pre-trained word embeddings
- RNNs for translation, sentiment detection and other text applications
- Case study 2: Neural Networks for NLP Lab
- Designing NLP Applications
- Data scraping and acquisition: Edgar, StockTwits, Twitter
- Text Summarisation
- Conversational agents-Chatbots
- Sentiment analysis
- Document Classification
- Case study 3: Illustrations on various NLP techniques using Python
Case studies and frontier topics
- Pipelines for NLP: Data ingestion, pre-processing, feature extraction, model selection and deployment
- Frontier topics
- The future of text applications
- Developing applications with QuSandbox
- Case study 1: Sentiment analysis in Keras
- Case study 2: Text Summarization using Encoder-Decoder models
Sample Content from a prior workshop
Past Attendees of QuantUniversity workshops include Assette, Baruch College, Bentley College, Bloomberg, BNY Mellon, Boston University, Datacamp, Fidelity, Ford, Goldman Sachs, IBM, J.P. Morgan Chase, MathWorks, Matrix IFS, MIT Lincoln Labs, Morgan Stanley, Nataxis Global, Northeastern University, NYU, Pan Agora, Philips Health, Stevens Institute, T.D. Securities and many more..