Neo4j Live: Graph-Based Linguistics
Play video on YouTube: Neo4j Live: Graph-Based Linguistics
Up next
Road to NODES AI: Graph-Based Long-Term Memory: How Agentic Workflows Adapt Through Experience
Maria Di Maro is a Post-Doc at the University of Naples ‘Federico II’. She got her Ph.D. in 2021 with a thesis in Linguistics with a focus on graph-based models to represent and manage Common Ground in dialogue systems, especially regarding inconsistencies in the Common Ground and the consequent elicitation of clarification requests are concerned.
We define Common Ground Inconsistencies as the incompatibility between the listener belief and the new evidence provided by the speaker.
In this talk, she will discuss using graphs for linguistic purposes. She will emphasise the potential of graphs in extracting information more intricate and detailed than corpus linguistics and basic text-based statistical models. Mainly, she will focus on how graphs can enhance the analysis and modelling of communication in pragmatics, a branch of linguistics focusing on language in use.
Resources mentioned
- Neo4j Live: Conversational Artificial Intelligence With Neo4j and Unreal Engine
- Di Maro, Maria, Antonio Origlia, and Francesco Cutugno. "Conflict Search Graph for Common Ground Consistency checks in Dialogue Systems." Proceedings of the 25th Workshop on the Semantics and Pragmatics of Dialogue. 2021. (opens in a new tab)
- Origlia, Antonio, Martina Di Bratto, Maria Di Maro, Sabrina Mennella. "A Multi-source Graph Representation of the Movie Domain for Recommendation Dialogues Analysis." Proceedings of the Thirteenth Language Resources and Evaluation Conference. 2022. (opens in a new tab)


