Hai Dang Tran after defending his thesis with his supervisors Gerhard Weikum (2nd from left) and Anrew Yates (3rd from right). Photo: MPI-INF. Photo: MPI-INF
On July 18, Hai Dang Tran successfully defended his PhD thesis entitled “Incorporating Knowledge about Entities in Conversational Search”. Hai Dang Tran joined Saarland University and the Max Planck Institute for Informatics in February 2021 as a doctoral candidate under the supervision of Prof. Andrew Yates and Prof. Gerhard Weikum. He was a member of both the Saarbrücken Graduate School of Computer Science and the International Max Planck Research School. His doctoral degree was awarded by Saarland University.
The abstract of his Thesis:
Although trained on a vast amount of data, language models (LMs) struggle to fully capture information about entities. This issue is especially noticeable for tail entities, which are sparsely covered or entirely absent from knowledge bases. Modern information retrieval (IR) methods rely on language models. Therefore, they struggle to interpret tail entities and questions about them. To bridge this gap, we propose incorporating knowledge about entities into LM-based models in information retrieval. Our first IR method, EVA, addresses the challenge of leveraging knowledge about entities to understand questions. Our second method, CONSEN, tackles the challenges of contextualization and handling informal questions in conversational IR setting. This approach particularly focuses on the challenge of understanding questions about tail entities. We propose our third method, EECATS, to fight three challenges simultaneously: contextualizing questions, handling long-tail entities in conversational IR, and maintaining efficiency for interactive responses.