At DFKI's LT lab we have developed a robust and efficient shallow NL
core system for information extraction from real-world German
text. The system called SMES consists of domain-independent shallow
core components which are realized by means of cascaded weighted
finite state machines and generic dynamic tries. German text
processing includes (among others) compound processing, high
performance named entity recognition, chunk parsing based on a
divide-and-conquer strategy, and shallow reference resolution. SMES
has a good performance (more than 5000 words per second on standard PC
environments) and high linguistic coverage.
If you would like to meet with the speaker, please contact: