Recent Works on Question Generation From Knowledge Graphs & Text
|
Speaker (s):
Yuan-Fang Li
Senior Lecturer
Monash University
|
|
Date:
Time:
Venue:
|
|
October 16, 2019, Wednesday
2:30pm - 3:30pm
SIS Meeting Room 5.1, Level 5
School of Information Systems
Singapore Management University
80 Stamford Road
Singapore 178902
|
|
ABSTRACT
Automatically generating questions has many applications in diverse fields. In this talk, I will present our recent works on automatic question generation (QG) over knowledge graphs and text. In text-based QG, I will present a number of techniques that generate question-answer pairs from a given passage of text. In KG-based QG, I will present a neural network-based method for automatic generation of complex multi-hop questions over knowledge graphs, which, taking a subgraph and an answer as input, generates a difficulty-controllable natural language question. Our evaluation shows that our models are able to generate high-quality, fluent and relevant questions.
ABOUT THE SPEAKER
Yuan-Fang Li is a Senior Lecturer at Faculty of Information Technology, Monash University. Yuan-Fang received his Bachelor of Computing (Honours) and PhD from School of Computing, National University of Singapore (NUS). His research interests include knowledge graphs, knowledge representation and reasoning, ontology languages, natural language processing, and software engineering.
