Weakly Supervised Learning in Text Mining: Utilizing Supervision from Text and Graph Data

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


PhD Thesis Defence


Title: "Weakly Supervised Learning in Text Mining: Utilizing Supervision 
from Text and Graph Data"

By

Miss Ziqian ZENG


Abstract

Currently, supervised learning based methods and techniques such as deep 
learning methods, have achieved great success in the text mining area. 
When researchers develop these giant models, they usually assume the 
availability of massive annotated training data. However, the real-world 
usefulness of these models will be impaired because in the real world, 
readily available annotated data are scarce. Fortunately, there are many 
inexpensive and readily available resources that can provide supervision. 
We show how to utilize supervision in text and graph data in the sentiment 
analysis, text classification, and the personalized word embeddings task. 
For example, for sentiment analysis, supervision can be opinion words in 
the text. For text classification, supervision can be generated words from 
a masked language model via querying about the topic of a document. For 
personalized word embeddings learning, supervision can be corpora of 
users’ friends via a social graph. To utilize supervision signals from 
text data, we propose a variational weakly-supervised framework for the 
sentiment analysis task and the text classification task. To utilize 
supervision signals from graph data, we propose a personalized word 
embeddings model with a social network based regularization.


Date:			Thursday, 10 June 2021

Time:			2:00pm - 4:00pm

Zoom Meeting: 
https://hkust.zoom.us/j/99597438576?pwd=S1AwNlZvRmwyOU4rTXFTTEhPUkJPUT09

Chairperson:		Prof. Tao LIU (PHYS)

Committee Members:	Prof. Yangqiu SONG (Supervisor)
 			Prof. Xiaojuan MA
 			Prof. Dit Yan YEUNG
 			Prof. Yi YANG (ISOM)
 			Prof. Jialin PAN (NTU)


**** ALL are Welcome ****