Building a Question Answering System using Deep Learning Techniques

Loading

Follow to receive video recommendations   a   A


Question Answering is an active area of research where the goal is to provide brief and crisp answers to natural language questions. Given a question and a text passage, the task is to answer the question based on the information given in the passage. Traditionally, NLP techniques like noise removal, tokenization, dependency parsing, named entity recognition etc. are used to extract an answer from the passage. With Deep Learning techniques gaining traction, the focus has now shifted to how neural network architectures can improve the accuracy of Question Answering Systems. This talk will help the audience understand how QA systems work and enable them to build one on their own! Talk Outline : 1. Introduction to Question Answering(Reading Comprehension, in particular) 2. Discuss available datasets 3. Baseline Approach to solving the problem using NLP techniques 4. Walk through the pipeline of deploying Deep Learning models (i.e. preprocessing dataset, generating word embeddings, building an encoder-decoder model using LSTMs, attention networks and evaluating it)

Pre-requisites: Python, Basics of Neural Networks and NLP, Keras



Editors Note:

I would like to work with open source projects to create a branch of the tree with all of the best videos for your open source project. Please send me an email if you are interested.