Essam Mansour
Associate Professor
CanadaResearch Interests
Explore related searches
Positions (1)
Essam Mansour
Concordia University
8 months ago
Concordia University, under the leadership of Associate Professor Essam Mansour, is seeking outstanding PhD graduates and postdoctoral fellows to join a high-impact research program in Agentic Enterprise AI and intelligent data systems. This opportunity is part of the new Canada Impact+ program, which aims to attract top-tier research talent to Canada. The research group focuses on building AI-native, enterprise-grade intelligent data systems, with key areas including agentic AI, multi-agent LLM systems for enterprise workflows, semantic data layers (such as knowledge graphs, ontologies, retrieval-augmented generation, and vector plus relational systems), and trustworthy generative AI for data infrastructure. Successful PhD candidates will receive $40,000 per year for three years, while postdoctoral fellows will receive $70,000 per year for two years. The program is well-funded and features strong industry collaborations in both Canada and the USA, offering opportunities for real-world impact beyond academic prototypes. Ideal candidates for the postdoctoral position should have at least one publication at top venues such as SIGMOD, VLDB, ICDE, NeurIPS, AAAI, ACL, EMNLP, or CCS. Applicants should have a strong background in AI, data systems, and related fields. No specific GPA or language test requirements are mentioned. To apply, interested candidates should send their CV and research interests to Professor Essam Mansour at [email protected], using the subject line 'Canada Impact' to discuss fit and nomination for the Impact+ program. For more information about Professor Mansour and his research, visit his LinkedIn profile .
8 months ago
Articles (1)
Knowledge from diverse application domains is organized as knowledge graphs (KGs) that are stored in RDF engines accessible in the web via SPARQL endpoints. Expressing a well-formed SPARQL query requires information about the graph structure and the exact URIs of its components, which is impractical for the average user. Question answering (QA) systems assist by translating natural language questions to SPARQL. Existing QA systems are typically based on application-specific human-curated rules, or require prior information, expensive pre-processing and model adaptation for each targeted KG. Therefore, they are hard to generalize to a broad set of applications and KGs. In this paper, we propose KGQAn, a universal QA system that does not need to be tailored to each target KG. Instead of curated rules, KGQAn introduces a novel formalization of question understanding as a text generation problem to convert a question into an intermediate abstract representation via a neural sequence-to-sequence model. We also develop a just-in-time linker that maps at query time the abstract representation to a SPARQL query for a specific KG, using only the publicly accessible APIs and the existing indices of the RDF store, without requiring any pre-processing. Our experiments with several real KGs demonstrate that KGQAn is easily deployed and outperforms by a large margin the state-of-the-art in terms of quality of answers and processing time, especially for arbitrary KGs, unseen during the training.
Year:
2023
ApplyKite TwinLearns as you applyMake your next move.
Prepare your application
Review drafts before you send them.