Algorithms for
Algorithms for Linguistic Processing is a NWO PIONIER research project in the area of computational linguistics. The project focuses on problems of ambiguity and processing efficiency by investigating grammar approximation and grammar specialization techniques.
Project duration: 2000-2005.
- Final Report
- WORKSHOP November 11, 2005
- television
interview in Adams Appel. The annotations produced by Alpino for the
sentences from the tv-news used in the program are here
- Mid-term progress report
ALPINO As part of PIONIER we are constructing a
natural language understanding system for Dutch. This ever-growing
system includes a wide-coverage grammar
HPSG for Dutch, a large-scale lexicon, a parser, a disambiguation
component using a log-linear (maximum entropy) model etc. There is an
experimental
web-demo. Experimental binary and source distributions are
available (at your own risk!) here.
- A1 poster of Alpino (in Dutch)
- Annotation efforts. As part of PIONIER we are annotating various
small corpora of Dutch with CGN dependency
structures. Although this is work in progress, you can browse this material on the web.
- Various texts describing the project
- Full Proposal [html,postscript,pdf]
- A short description in Dutch
- An attempt to explain the goals of the project for non-specialists (in Dutch too)
- A somewhat longer description in English
- NWO Onderzoekberichten
- Persinformatie RuG
- Descriptions of a number of sub-projects, taken from the BCN annual report
1999-2001:
- Empirical Aspects of Finite State Processing
- Computational aspects of modification in fixed expressions
- Alpino : Computational syntactic analysis of Dutch
- Expressiveness of grammatical formalisms and efficiency of syntactic processing
- Statistical Parsing
- Lexically sensitive disambiguation techniques
- Project Members, Associated Members, Former Members