During the last ten years, the NLP-group at the Department of Computer Science, University of Turin, developed a Morphological analyzer, a Tokenizer and a Chunk-rule based dependency Parser in Allegro Common Lisp. They constitute the Turin University Linguistic Environment (TULE): a linguistic framework that takes a NL sentence in input and returns a dependency tree describing its syntactic structure.
The TULE research project is part of the activity of The Interaction Models Group.
TULE currently supports two languages: Italian and English. Extensions to Spanish, Catalan, French and Hindi are under development. TULE adopts a representation format based on the dependency paradigm centred upon Augmented Relational Structure (ARS), where each relation is implemented as a feature structure that can include values for morpho-syntactic, functional-syntactic, and syntactic-semantic components.
TULE has been involved in several Projects, the most relevant one being the Turin University Treebank (TUT), a
Treebank including 2,200 Italian sentences and 200 English sentences. TULE has been used for the semi-automatic annotation of the sentences included in TUT.
TULE e TUT share the same representation format. More information about TUT and the representation format are available at the TUT site.
TULE is available as a Server. You can download a Java client from here, send NL sentences to TULE, and graphically display the resulting dependency trees on your screen!