|Name||Orphée De Clercq|
|Telephone number||+32 9 33 11 938|
Orphee is particularly interested in modeling deep semantic knowledge in order to better grasp this multifaceted aspect of natural language. Her main research focus has been on devising and employing deep semantic processing systems for readability prediction and fine-grained sentiment analysis of user-generated content. During her postdoc-project Orphee is further elaborating on her readability research. Her main objectives are to (1) investigate domain portability and (2) move towards automated writing evaluation. At the same time she is exploring new techniques for porting her Dutch fine-grained sentiment analysis pipeline to different domains and languages. She is teaching new courses on translation technology and digital communication using blended learning techniques.
After obtaining her Master's at the Faculty of Applied Language Studies, Orphée became a member of the LT3 research team where she was introduced to the fascinating field of computational linguistics. During her first work on various research projects at the LT3 team she was responsible for the compilation of some prestigious Dutch corpus projects and the (semi)-automatic annotation of various semantic layers. She has devised new tools for coreference resolution and semantic role labeling. The latter while she was partially employed at the University of Utrecht.
In more recent years, she has developed a full-fledged readability prediction system for Dutch and English generic text with a focus on the added value of incorporating more semantic knowledge. In the spring of 2014, Orphée spent a semester at the University of Mannheim where she performed research on adding deep semantics to content-based book recommenders and combining sentiment analysis techniques with information derived from linked open data. During her work on the PARIS project she was responsible for the deep linguistic processing of user-generated content. In the summer of 2015 Orphée obtained her PhD, in her dissertation she investigated the impact of incorporating semantic features on the performance of high-end applications such as automatic readability prediction and sentiment analysis.
She is currently employed at LT3 as a postdoctoral research assistant and continues her work on readability prediction and sentiment analysis.