I am investigating computational models for linguistic structures and processes, with application to language technologies and to the documentation of endangered languages. My current focus is on efficient query for databases of hierarchically annotated data. After completing a PhD on computational phonology at the University of Edinburgh in 1990, I worked on a series of European research projects and conducted linguistic fieldwork in Cameroon with SIL. In 1998 I moved to the University of Pennsylvania, becoming Associate Director of the LDC, and working on models and tools for linguistic annotation. In 2002 I returned home to Australia and established the Melbourne University Language Technology Group. In 2007 I was awarded the Kelvin Medal for excellence in teaching.
Key Activities: Coordinating first year Informatics; developing the Natural Language Toolkit; writing a textbook on NLP; leading the Language Technology Group; working on an NSF project on Querying Linguistic Databases; and editing Cambridge Studies in Natural Language Processing and the ACL Anthology.
Key Publications: Natural Language Processing in Python; Computational phonology: A constraint-based approach (Cambridge); A formal framework for linguistic annotation (Speech Communication); Seven dimensions of portability for language documentation and description (Language); Designing and evaluating an XPath dialect for linguistic queries (ICDE).
The Talking Heads experiment raises questions in three areas of research: How do words get their meanings? Is artificial intelligence possible? How should machines interact with humans?
Online Demo of the TreeTagger. A tool for annotating text with part-of-speech and lemma information which has been developed at the Institute for Computational Linguistics of the University of Stuttgart.
Shalmaneser is a supervised learning toolbox for shallow semantic parsing, i.e. the automatic assignment of semantic classes and roles to text. The system was developed for Frame Semantics; thus we use Frame Semantics terminology and call the classes frames and the roles frame elements. However, the architecture is reasonably general, and with a certain amount of adaption, Shalmaneser should be usable for other paradigms (e.g., PropBank roles) as well. Shalmaneser caters both for end users, and for researchers.
Alle Programme und Resourcen auf der Liste sind frei, d.h. kostenlos (für Forschungszwecke) verfügbar, auf deutschsprachige Texte anwendbar und sofort startklar, d.h. sie müssen nicht erst mit Hilfe von z.B. annotierten Korpora trainiert werden. Die Liste ist natürlich unvollständig (Stand 22.5.2007).