Student research wins best paper at international FinTech workshop
A recent graduate of Carnegie Mellon University in Qatar (CMU-Q), a Qatar Foundation partner university, took the Best Paper award at an international workshop on Natural Language Processing (NLP) for financial technology applications. Samir Abdaljalil, who graduated in May 2021 with a bachelor’s degree in information systems, conducted this research for his senior honors thesis.
For the project, Abdaljalil explored the use of NLP, machine learning and deep learning techniques to build automatic summarization systems of financial reports. With the average financial document weighing in at about 180 pages, automatic summarization could save time and simplify the task of identifying takeaways and key messages.
Houda Bouamor, assistant teaching professor of information systems and an expert in NLP and machine learning, supervised Abdaljalil’s research and is a co-author of the paper.
“This project was very challenging. It is difficult enough to summarize long documents, but financial documents also have very specialized language. Samir looked at the problem from many different angles and answered several questions such as: What is the nature of the datasets needed for such tasks? What is the most important information to extract from these kinds of documents What would be a good summarization model?”
To answer these questions, Abdaljalil turned to experts in finance, as well as previous investigations into NLP for similar applications.
“Samir did an amazing job,” Bouamor said. “NLP is a complex area of study, and not usually a field that undergraduates pursue. Samir asked the right questions, and he worked very hard to find solutions to those questions. I am proud of this achievement”
Abdaljalil and Bouamor presented the paper at the Third workshop on Financial Technology and Natural Language Processing (FinNLP 2021). The workshop was part of the 30th International Joint Conference on Artificial Intelligence (IJCAI 2021), one of the top ranked conferences in the fields of artificial intelligence and NLP.
Abdaljalil is now considering an academic career path to continue the research he started during his senior year at CMUQ: “After doing my honors thesis, I realized that I want to pursue Natural Language Processing further. As an Arab, I am particularly interested in NLP for the Arabic language, which is a relatively new area of study.”
For Bouamor, introducing students to research continues to be a passion: “CMU-Q students have the potential for being excellent researchers. I want to nurture those skills and show them that research can be a career, you can become an academic and spend your career working on things that fascinate you.”