DTAI Stories

Declarative Languages and Artificial Intelligence

More info about the DTAI research group

Articles

Sudoku Assistant – An AI Assistant Combining Machine Learning and Reasoning

We introduce The Sudoku Assistant, an AI assistant that integrates machine learning and reasoning to interpret, solve and explain pen-and-paper Sudokus scanned with a smartphone. The assistant demonstrates three increasingly important concepts in AI research: the integration of learning and reasoning, explainable AI and human-centered AI.

TorchicTab: Semantic Table Annotation

TorchicTab is a semantic table annotation system that automatically understands the content of a table and assigns semantic tags to its elements with high accuracy.

The Role of Counting in Probabilistic Reasoning

Do you know how to model count? We provide an introduction to model counting: what is it, why is it so important (hint: state-of-the-art probabilistic reasoning!), and what is the relation with knowledge compilation.

Lifted Reasoning for Combinatorial Counting

In this paper we develop lifted reasoning techniques for counting the number of valid configurations in combinatorics math word problems. Lifted reasoning exploits high-level symmetries and the interchangeability of objects to efficiently count the number of admissible assignments for a set of variables.

Real-time On-edge Acoustic Event Classification

Edge AI is the deployment of AI applications on embedded devices near the sensor, close to where the data is located, rather than centrally in a cloud computing facility or a data center.