Data Management for Artificial Intelligence: When Natural Language Processing meets Databases

André Freitas
University of Passau, Germany

2:15pm-3:15pm, 8 May 2017
EM 3.06


The recent evolution of approaches, data resources and tools in the Natural Language Processing (NLP) field brings the opportunity for the construction of data management infrastructures and analysis methods which are able to work over unstructured, complex and semantically heterogeneous data. The ability to systematically structure, integrate, query and operate over large-scale/high-variety data emerges as a strong demand across different Artificial Intelligence (AI) applications. In this talk, we will describe information extraction, knowledge representation and semantic parsing approaches which can operate over heterogeneous data and how these combined methods can be used to support the construction of the next generation knowledge-intensive AI systems.


André Freitas is a research group leader and lecturer at the Natural Language Processing & Semantic Computing research group at the University of Passau in Germany. Before joining Passau, he was part of the Digital Enterprise Research Institute (DERI) at the National University of Ireland, Galway, where he did his PhD on Schema-agnostic Query Mechanisms for Large-Schema Databases. His main research areas include Question Answering, Schema-agnostic Databases, Natural Language Query Mechanisms over Large-Schema Databases, Distributional Semantics, Hybrid Symbolic-Distributional Models, Approximate Reasoning and Open Relation Extraction.