Graphic is from the paper “Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding”

The Spring 2022 semester was a memorable one for Ph.D. student Sijia Wang.

The Association for Computational Linguistics (ACL) accepted the paper, “Query and Extract: Refining Event Extraction as Type-oriented Binary Decoding,” which she is presenting on May 24 during its international meeting in Dublin. 

And she is part of the Virginia Tech team from the Sanghani Center that is one of 10 finalists chosen to compete in the Alexa Prize SimBot Challenge. The challenge focuses on advancing the development of next-generation virtual assistants that continuously learn and gain the ability to perform common sense reasoning to help humans complete real-world tasks. 

Wang’s specific role on the team — advised by Lifu Huang, who is also her academic advisor — is to establish knowledge graphs from instructional articles, images, and video demonstrations on the internet, such as WikiHow. She will also concentrate on collectively grounding entities and actions extracted from text to video to associate each entity or action with a visual image or video clip.

In her research, Wang focuses on natural language processing and machine learning, particularly  information extraction with full or limited supervision. 

Information extraction, she said, poses challenges because of its sophisticated annotation needs and variance benchmarks, she said. 

“I am trying to automatically extract structured information from unstructured data,” Wang said. “For example, in the sentence ‘Melony was married just a month before she left for Iraq,’ the word ‘she’ indicates Melony, and her marriage occurs before the movement event. My research focus is to extract this information from the input sentence.”

Wang said that as a young child she wanted to understand foreign languages but knew that it would take a great effort to do so. “When I learned about machine learning as an undergraduate student, I was really drawn to it because of how we can use its model fitting and pattern learning abilities to automatically understand visual content.”  

Wang holds a bachelor’s degree in vehicle engineering from Southwest Jiaotong University in China and a master’s degree in computer science from Washington University in St. Louis. She was drawn to Virginia Tech and the Sanghani Center for a Ph.D. computer science program because of the experienced professors and their cutting-edge research in artificial intelligence and data science. “Their work and achievements and all the passionate students around me have motivated me to work harder,” she said.

Being a Ph.D. student has made her realize how much time and effort it takes to become a successful academic researcher, she said. “So after graduation, I will be looking for a postdoc position or other research opportunities at private and research labs to become better equipped to become a research scientist.”

Wang is projected to graduate in 2024.