UGOT: patent case study partner - nothing decided yet - ongoing discussing with EPO, AR is waiting reply from EPO
Kiril Simov has not replied for Varna - so no invited speakers so far
AR and OC will prepare the progress report to be completed in Varna by partners
AR: do we have internet in Varna?
PM: not sure about the internet situation in Varna - will bring router to Varna
AR: phrasebook led to experiments and ideas for tools, work is proceeding as expected
OC: ACL2010 meeting went well - AR, maybe LREC better venue for MOLTO
UHEL: LC put a draft on the wiki, difficulty is in getting info from users, afraid that WP are so independent until very end, and user testing gets done only in the end -- time scheduling to be reviewed in Varna (1 hour time in varna minimum to discuss)
UHEL wiki is open as sketchpad
UHEL is winding up another project and produced a tool for multilingual ontologies - will present it in Varna (project is ConFactory) - Inari and LauriA will probably work in a group with Petar on Ontologies
UPC: SMT group, cristina asked access to carry out patent study - but very slow
WP6, started with modularize webalt grammars, stuck now on german, naive approach: add new language by changing the lexicon and seeing if it compiles -- no idea what will happens with languages such as bul, fin, etc.
AR: let's get few languages in high quality first, then scale up
JS: eng spa, cat fre, ita, in the OpenMath layer compile
JS: cristina and ramona worked on integration run some experiments to create statistical model from GF generated parallel corpora -- also made word alignment in GF
JS: python plugin for GF in contrib folder -- it is a shared library can be imported in GF so one can open a pgf file from python to check grammars, linearize
expect to be difficult to integrate into main python core NLTK - easier to get into contrib
Onto: onto worked on 1. knowledge rep infrastructure 2. grammar ontology interoperability - demo planned for varna for #2
AR made GF query grammar - linked to ontology of ontotext so that natural language queries are executed by semantic engine
UI will be shown in Varna, uses autocompletion from gf
some efficiency problem being discussed with Krasimir, most likely our virtual machine makes things slower
AR: is query grammar enough or needs extension?
PM: maybe another case study can prove the point of ontology-grammar interoperability: lexicon is kept separate from grammar - it is generated from the ontology
PM will ask Simov tomorrow
Cristina might not be there on 1st day (amend program)
LC could get some material on evaluation of MT systems but not really a tutorial
Day 3 WGs :
Logistics: maybe 3 rooms for day 3 and larger room for day 1