Deep Learning Approaches for Question Answering System

Deep Learning for Visual Question Answering

This project deals with the problem of Visual Question Answering (VQA). We develop neural network-based models to answer open-ended questions that are grounded in images. We used the newly released VQA dataset (with about 750K questions) to carry out our experiments. Our model makes use of two popular neural network architecture: Convolutional Neural Nets (CNN) and Long Short Term Memory Networ...

Visual Question Answering using Deep Learning

Multimodal learning between images and language has gained attention of researchers over the past few years. Using recent deep learning techniques, specifically end-to-end trainable artificial neural networks, performance in tasks like automatic image captioning, bidirectional sentence and image retrieval have been significantly improved. Recently, as a further exploration of present artificial...

Learning Components for A Question-Answering System

Empirical Study on Deep Learning Models for Question Answering

In this paper we explore deep learning models with memory component or attention mechanism for question answering task. We combine and compare three models, Neural Machine Translation [1], Neural Turing Machine [5], and Memory Networks [15] for a simulated QA data set [14]. This paper is the first one that uses Neural Machine Translation and Neural Turing Machines for solving QA tasks. Our resu...

A Deep Learning Approach for Question Answering Over Knowledge Base

With the increase of the scale of the knowledge base, it’s important to answer question over knowledge base. In this paper , we will introduce a method to extract answers from Chinese knowledge base for Chinese questions. Our method uses a classifier to judge whether the relation in the triple is what the question asked, question-relation pairs are used to train the classifier. It’s difficult t...