This is a past event
Abstract: Natural language plays an increasingly important role as interface to existing services and data. However, a number of characteristics of today’s language technology make it hard to be adopted by non-linguistically skilled developers. I present an architecture that supports the easy adoption of language technology into existing applications, building on two major aspects: First, a conceptualization of the application scopes the language fragment that needs to be supported, in particular limits and tailors all interpreted and generated language. And second, the creation and use of resources is highly modular, separating three dimensions: domains, tasks, and languages. Finally, I show an implementation of this architecture based on the ontology-lexicon format lemon and Grammatical Framework.
Link: purl.org/3dlt/home
Bio: Christina Unger is a postdoctoral researcher in the Semantic Computing group affiliated to the Cluster of Excellence on Cognitive Interaction Technology (CITEC) at Bielefeld University, Germany. She received her PhD from the Utrecht Institute of Linguistics (UiL-OTS), the Netherlands, in 2010, in the area of computational semantics. Her major research interest are natural language interfaces to structured data, with a focus on ontology-based natural language understanding, question answering over RDF data, and the automatic induction of grammars from the lexicon-ontology interface.
- Speaker
- Christina Unger
- Hosted by
- Adam Wyner
- Venue
- MT 203