A Survey on Abstract Meaning Representation

PhD Qualifying Examination


Title: "A Survey on Abstract Meaning Representation"

by

Miss Ziyi SHOU


Abstract:

Understanding the meaning of natural language has been a long-time goal in 
the field of artificial intelligence. Under the idea that the meaning of 
linguistic expression can be captured in formal structures, the need for 
meaning representations arises. Abstract Meaning representation (AMR) is a 
typical meaning representation framework that represents a sentence’s 
meaning as a directed graph with concepts as labeled nodes and relations 
as directed edges. This survey serves as a systematic review of AMR. 
First, we compare different methods of producing AMR from linguistic 
expression and point out their weaknesses and possible solutions. Then, we 
review another classic meaning representation task, the generation task, 
which is to synthesize sentences given AMR annotations. Finally, we list 
some applications using AMR and discuss other possible directions.


Date:			Tuesday, 15 June 2021

Time:                  	2:00pm - 4:00pm

Zoom meeting:
https://hkust.zoom.us/j/95717344517?pwd=OEIzTHRFR0c0N2ZSSEJaS3IxQnAwUT09

Committee Members:	Prof. Fangzhen Lin (Supervisor)
 			Prof. Cunsheng Ding (Chairperson)
 			Dr. Yangqiu Song
 			Prof. Nevin Zhang


**** ALL are Welcome ****