Mateva 10:02 AM good morning Olga Caprotti 10:05 AM Agenda status report email aarne AR: working with finishing deliverabe in WP8 with ontotext AR: and hybrid translation with UPC - AR: new PO is called Pierre-Paul Sondag Aarne Ranta 10:06 AM Pierre-Paul.Sondag@ec.europa.eu Olga Caprotti 10:08 AM AR: emails shared only for confidential matters - he is expected to email only with coordinator AR: would be good if some partners come to BCN one day ahead for last project meeting (wedn) LC: last friday had call, integration in progress - LA is working on it, IL workig on TF to GF translation LC: sticking to GlobalSight LC: other platforms are just computer translation tools and translators cannot change the source original, whereas I always thought MOLTO tools need to allow for feedback during the working time. Also it has to be a community and not a single translator, this is what GS does. The workflow is the most interesting part. LC: community aspect of usage of MOLTO tools is the interesting part LC: using grammars to populate translation memories is work in progress - LA started on that AR: pls change the date of D3.3 LC: D3.3. will be due by 31 March 2013 at the very latest LC: concern by Jussi on evaluation AR: Jussi should send some TODO MM: would like to have TODOs for each WP evaluation LC: checklist evaluation probably LC: bilateral discussions on how to carry out evaluations AR: pls use the google group to keep everyone informed JS: WP5 and WP6 no news to report, WP7 evaluation is being organized JS: concerned about flagship and wiki, we are supposed to use the wiki for the flagship - eg how to do the latex OC: we will use mathjax OC: linear algebra topic for demo MM: WP7 prototype being finalized. Ontotext requested many changes to the grammar to cover the ontology MM: retrieval system is being optimized (snippetting) MM: plan to finish draft of final deliverables by end of Feb, but delayed, if we need to do internal evaluation, then deadline will not be met. D7.3 is basically beingheld due to evaluation. MM: also working on WP8 so prefer to concentrate on WP7 first with short deadline AR: for the patent queries, RE made a SPARQL translation - does it work? MM: yes, system accepts both old and new queries. coverage of new grammar not so large - lexicon help needed AR: basically polishing details MM: WP8 had a deadline for query grammar to end of month. we worked on bulgarian mainly AR: query grammars all in place for WP8 - goal to have same languages as for the texts MM: fix what to adopt - old or new generation in SPARQL MM: prefer the new way to generate SPARQL directly MM: draft of KB for WP8 MM: mariana is working on MNL chapter for book AR: should wrapt up the deliverables and focus on demo NEF: summary sent OC: will be in minutes NEF: what sharing should be with Jussi and ourselves in evaluation NEF: UZH will do usability test and UHEL will do translation quality NEF: test sentences for Jussi ready - but grammatically ok but semantically nonsense NEF: long discussion on user evaluation of the wiki - we will use geography in ES DE EN NEF: vocabulary of 500 words, problem of proper names (google group discussion ongoing) NEF: we will have test persons writing sentences (choppy) NEF: deliverable 11.2 NEF: sw is permanently undr revision NEF: pointer to exact version of sw described in deliverable is already there as comment by Kaarel NEF: we are working on a constructive counter proposal to AR's flagship demos NEF: since many things in there have not been promised and we are unsure to be able to do them Lauri Carlson 10:45 AM I lost voice connection, reduced to reading the chat Sad Olga Caprotti 10:45 AM NEF: tobias decision to work half time allowed us to hire 2 extra persons. we are in a better shape with larger groups - lots of discussions JvA: evaluation results getting closer JvA: grammars on business models are final, models can be exported to OWL and back JvA: first explanation sentences can be generated - all in English for now - translations maybe within 1 or 2 weeks JvA: EN DUT ES DE targeted JvA: evaluation will be carried out on those sentences compared to our current approach JvA: flagship - we know what we want to show. Internal evaluation with BeInformed people - to see if explanations are better than before JvA: if you want to see our data for evaluation, let me know. JvA: will send to Jussi, EN and all langs when I get them JvA: performance evaluation and evaluate how to get grammars JvA: our current way to get explanations is very different from how we did in the past - how to evaluate it is new also. AR: are you specifying whcih skills are needed for each task? JvA: yes. we still need to finalize the integration in our tool in order to evaluate that. MM: is there a demo we can see? MM: the lemon integration is very interesting JvA: will post to the google group. JvA: setup a telco on exploitation MM: lets setup a meeting - Borislav must be present OC: volunteer for next google hangout 11:03 AM Call ended1 hour 1 minute