Development of classification module for automated question generation framework

Automated Question Paper Generation System

n today’s age, education is the most important way of achieving success. When we discuss education, it is imperative to mention tests and examination. Examinations prepare students in their quest for knowledge. So, having a proper examination paper and format is quite necessary. Now the traditional method of generating question paper has been manual. In this method certain officials chalk out t...

CS229 Final Project: Enhancing Automated Question Classification

This class project investigated improving classification of short questions. We first established a baseline for further work by comparing a number of different off-the-shelf classifiers. We gathered a new corpus to add to ones already available. We then implemented and applied semisupervised classification, adding large amounts of unlabelled data in an attempt to boost classification accuracy....

Automated Template Generation for Question Answering over Knowledge Graphs

Templates are an important asset for question answering over knowledge graphs, simplifying the semantic parsing of input utterances and generating structured queries for interpretable answers. Stateof-the-art methods rely on hand-crafted templates with limited coverage. This paper presents QUINT, a system that automatically learns utterance-query templates solely from user questions paired with...

Development of a 200MHz Clock Generation Module

Question Generation for Question Answering

This paper presents how to generate questions from given passages using neural networks, where large scale QA pairs are automatically crawled and processed from Community-QA website, and used as training data. The contribution of the paper is 2-fold: First, two types of question generation approaches are proposed, one is a retrieval-based method using convolution neural network (CNN), the other...