Relation Discovery with Out-of-Relation Knowledge Base as Supervision

MPhil Thesis Defence


Title: "Relation Discovery with Out-of-Relation Knowledge Base as 
Supervision"

By

Mr. Yan LIANG


Abstract

Unsupervised relation discovery aims to discover new relations from a 
given text corpus without annotated data. However, it does not consider 
existing human annotated knowledge bases even when they are relevant to 
the relations to be discovered. In this thesis, we study the problem of 
how to use out-of-relation knowledge bases to supervise the discovery of 
unseen relations, where out-of-relation means that relations to discover 
from the text corpus and those in knowledge bases are not overlapped. We 
construct a set of constraints between entity pairs based on the knowledge 
base embedding and then incorporate constraints into the relation 
discovery by a variational auto-encoder based algorithm. Experiments show 
that our new approach can improve the state-of-the-art relation discovery 
performance by a large margin.


Date:			Thursday, 4 July 2019

Time:			10:00am - 12:00noon

Venue:			Room 3494
 			Lifts 25/26

Committee Members:	Dr. Yangqiu Song (Supervisor)
 			Prof. Dit-Yan Yeung (Chairperson)
 			Dr. Brian Mak


**** ALL are Welcome ****