Posted on July 10, 2015
Orphée De Clercq successfully defended her PhD on July 9th, 2015. Her dissertation entitled Tipping the scales. Exploring the added value of deep semantic processing on readability prediction and sentiment analysis was supervised by Prof. dr. Véronique Hoste (Ghent University) and Prof. dr. Timothy Colleman (Ghent University). In her research she explored the added value of incorporating deep semantic information in two end-user applications that normally rely mostly on superficial and lexical information, viz. readability prediction and aspect-based sentiment analysis. For both applications she applied supervised machine learning techniques and focused on the incorporation of coreference and semantic role information. Her main conclusion is that for Dutch readability prediction deep semantic information, when integrated in a state-of-the-art classifier, does help to tip the scales on performance. By using such information for Dutch aspect-based sentiment analysis, she found that this approach does add weight to the scales, but cannot make them tip.