Hello, I’m a research assistant at National University of Singapore doing research in natural language processing, with applications in the detection of misinformation and toxicity on the web. Previously, I was at Plural AI, where I worked on entity extraction from webpages and semantic search, and at Donaco, where I worked on contextual recommendation of charity campaigns. I’m passionate about AI research, aiming to improve the way we discover and organize information.
MSc in Advanced Computing, 2017
Imperial College London
BSc in Computer Science, 2013-2017
Aristotle University of Thessaloniki
Plural AI is a fintech startup that builds a knowledge engine for the finance industry. The company focuses on extracting content from corporate websites and financial statements to enrich a financial knowledge graph, and support question answering on complex financial queries.
Donaco is an online advertising startup that tries to revolutionize online donations.
Passage retrieval is a part of fact-checking and question answering systems that is critical yet often neglected. Most systems usually rely only on traditional sparse retrieval. This can have a significant impact on the recall, especially when the relevant passages have few overlapping words with the query sentence. In this work, we show that simple training of a dense retriever is sufficient to outperform traditional sparse representations in both question answering and fact-checking. Our model is incorporated in a real world semantic search engine that returns snippets containing evidence related to questions and claims about the COVID-19 pandemic.