[12:58] == daveL [~daveL@public.cloak] has joined #mlw-lt [12:58] present+ daveLewis [13:00] == omstefanov [~omstefanov@public.cloak] has joined #mlw-lt [13:01] present+ omstefanov [13:01] == chriLi [~chriLi@public.cloak] has joined #mlw-lt [13:02] meeting: ITS IG [13:03] meeting: MLW-LT [13:03] chair: Dave Lewis [13:03] agenda: http://lists.w3.org/Archives/Public/public-i18n-its-ig/2013Jul/0058.html [13:03] == Jirka [~jirka@public.cloak] has joined #mlw-lt [13:04] rsagent, make log public [13:04] present+ Arle [13:04] present+ omstefanov [13:04] regrets: Jörg Schütz [13:04] present+ chriLi [13:04] present+ daveLewis [13:04] present+ Jirka [13:04] scribe: Arle [13:04] scribe Arle [13:04] * Jirka wonders why we are using different IRC channel then in dial-in info email [13:05] Hi jirka, we changed it last minute because enought WG topic have come up and we should prioritse minuting WG outcome [13:05] Jirka: There was an email saying because of MLW-LT business that would be default, with IG page linking to it [13:06] Topic: MLW-LT WG business: Minor changes [13:06] == philr [~philr@public.cloak] has joined #mlw-lt [13:06] present+ philr [13:08] apologies: jorge, felix, yves, [13:08] regrets: Yves, Felix [13:08] == leroy_ [~leroy@public.cloak] has joined #mlw-lt [13:08] present: christian, jirka, leroy, olaf, phil, arle, dave [13:09] agenda: http://lists.w3.org/Archives/Public/public-i18n-its-ig/2013Jul/0058.html [13:09] topic: MLW-LT WG business: Minor changes [13:09] Dave: We have a few MLW-LT working group topics. [13:09] .. Felix proposed some minor changes. [13:09] http://lists.w3.org/Archives/Public/public-multilingualweb-lt/2013Jul/0021.html [13:10] .. No objections [13:10] Arle: Seem like reasonable clarifications. [13:10] topic: MLW-LT WG: script topic [13:11] == kfritsche [~Karl@public.cloak] has joined #mlw-lt [13:11] http://lists.w3.org/Archives/Public/public-multilingualweb-lt/2013Jul/0014.html [13:11] Dave: Any objection to the proposal from Felix. [13:12] .. There was no perfect solution, but we tried to work with the relevant people to address this in the future, rather than changing the spec now. JSON is one possibility. [13:13] .. Some people have responded favorably on the email list. [13:13] Olaf: No win-win is possible. So we stick with what we have and look for 2.x or 3 for better solutions. [13:13] .. No one objected. [13:14] Dave: I've already set up in the IG tracker something for requirements not addressed in 2.0. This could go there. [13:14] Action: dlewis6 to raise issue of addressing script topic for 2.x in IG. [13:14] * trackbot is creating a new ACTION. [13:14] <@trackbot> Created ACTION-555 - Raise issue of addressing script topic for 2.x in IG. [on David Lewis - due 2013-07-24]. [13:15] present+ kfritsche [13:15] Topic: MLW-LT WG: mt confidence [13:16] arle: agrees with yves that a confidence score could be generated separately from mt engine itself [13:17] phil: how does confidence score relate to conformance score [13:18] arle: yes there are relations [13:19] olaf: but it seems unclear if we mean an advance score before fact or after fact [13:19] ... and there is a need to have multiple instance of MT confidence [13:19] arle: usually confidence score is returned after the target [13:21] Dave: I can ask internally about this for those working on these topics. Isn't QE a source measure looking at source and training data? [13:26] arle: for quality estimation with lucia specia this is definitely an assessment of the translation [13:26] dave: in this case would it be the same of LQI conformance type [13:26] arle: but isn't this just a switch [13:27] phil: but it does give a score [13:27] ... and has the advantage that it provides a standoff for multiple conformance annotaitons [13:27] we also should make sure we get Serge Gladkoff and Yves' comments on whatever final text we develop. [13:28] action: dlewis6 to consult with MT expert in CNGL for clarification [13:28] * trackbot is creating a new ACTION. [13:28] <@trackbot> Created ACTION-556 - Consult with MT expert in CNGL for clarification [on David Lewis - due 2013-07-24]. [13:28] == Ankit [~Ankit@public.cloak] has joined #mlw-lt [13:30] ankit can you join the audio [13:30] just a sec,, [13:31] Christian: What is the goal of discussion? To address ITS 2.0 or 2.x? [13:31] .. We just need some clarity [13:35] Ankit: ITS could use MT confidence to address both traditional MT confidence and QE. [13:36] Dave: The specific issue was whether it is self-reported (the spec talks about an MT engine self-reporting a score). If there is no bitext, that is then a quality estimation. We could have multiple, so we can't handle the issue of multiples in the current set-up. [13:37] .. There is also the conformance item in LQI, which could be used. [13:38] arle: using LQI does add some implementation weight [13:40] Topic: ITS IG: LQI-MQM mapping [13:41] arle: last week there was a call on how to address the MQM topic [13:41] ... two separable issue to be addressed [13:41] ... one is the mapping between MQM and LQI issue categories [13:41] .. this is fairly well solved with an exisitng mapping, though with some info lost in both directions [13:42] .. these can be dealt with in IG and documents [13:42] ... second issue is how to maintain the MQM work beyond the lifespan of the supporting project (QT-launchpad) [13:43] ... two possible homes are CRISP as GALA, or ITS IG [13:44] .. concensus in call was initially to do it in CRISP, but subsequently, GALA expressed preference to run it under ITS IG, led by DFKI initially [13:47] Arle: what is the deadline (end of life) of the EU project now developing MQM? [13:47] Arle: there are two different tasks - maintaining MQM category list, the other is the way to represent quality metrics with a defined reference to the quality profile [13:47] == Pedro [~Pedro@public.cloak] has joined #mlw-lt [13:48] ... so the latter is a fairly big technical task [13:48] Phil: asks if project is done under GALA, is GALA membership required? [13:48] arle: no, keen to avoid and cost barrier and CRISP is happy to work this way [13:49] ... then once there was consensus moving forward to a more formal standard, at W3C or elsewhere [13:49] which wiki? [13:49] thx [13:49] arle: on the IG wiki [13:50] phil: would be interest to be involved [13:51] .. but membership fee an issue [13:53] Action: Arle to add MQM products on the IG tracker [13:53] * trackbot is creating a new ACTION. [13:53] <@trackbot> Created ACTION-557 - Add MQM products on the IG tracker [on Arle Lommel - due 2013-07-24]. [13:53] We are member of GALA, if helps. [13:54] olaf: when does the current MQM proect end [13:54] arle: juen next year [13:54] ... looking for further funding already [13:54] s/juen/june/ [13:55] Dave: Yves isn't here so we don't have time to address the XLIFF/ITS mapping. [13:55] topic: ITS-IG XLIFF mapping [13:55] .. One small part for Phil. [13:56] .. I was putting LQR (rating) into the new mapping page on the IG page. Would LQR ever apply inline or only structural? [13:56] Phil: It is more structural. [13:56] .. But that led to confusion, but when we added voting, that adding confusion. When we discussed voting, it led to the requirement for inline. [13:57] Arle: We might want to note as best practice that you should use the biggest scope possible and keep it structural when possible. [13:57] action; dlewis6 to add LQR inline for voting and best practice note of using widest scope for this anntioan where appropriate [13:58] action: dlewis6 to add LQR inline for voting and best practice note of using widest scope for this anntioan where appropriate [13:58] * trackbot is creating a new ACTION. [13:58] <@trackbot> Created ACTION-558 - Add LQR inline for voting and best practice note of using widest scope for this anntioan where appropriate [on David Lewis - due 2013-07-24]. [13:58] Topic; IG wiki and action item tracker set [13:58] Topic: mechanics of moving issues from WG to IG. [13:59] s/mechanics of moving issues from WG to IG./IG wiki and action item tracker set/ [13:59] Dave; I'm leaving deliverables in the WG and moving community building, etc. to the IG. [13:59] Dave: what would be good is to get an email (and post to BOTH wikis) is to have a table of which things relate to which in both groups, with links to both the WG and IG pages. [13:59] s/Dave;/Dave:/ [14:00] .. I have separate products in the tracking to deal with XLIFF mapping, ontology, requirements, etc. [14:00] .. If other ones come up, we can add new products to associate actions and issues with them. We will only bring up ones associated with a product. [14:00] .. Any comments? [14:01] Arle: Good way to do it and the products will help keep us focused. [14:01] Dave: I'll talk to Felix about what to do with deliverables that could go in either the WG or IG. [14:02] happy holidays, Dave. [14:02] I'm off next wednesday, too. [14:03] bye [14:03] == Jirka [~jirka@public.cloak] has left #mlw-lt [Jirka] [14:03] == chriLi [~chriLi@public.cloak] has quit [""] [14:03] rrsagent, generate minutes [14:04] happy holidays! [14:07] == leroy_ [~leroy@public.cloak] has quit [Ping timeout: 180 seconds] [14:08] == omstefanov [~omstefanov@public.cloak] has quit ["Page closed"] [14:10] == Ankit [~Ankit@public.cloak] has quit ["Page closed"] [14:12] rrsagent, generate minutes [14:13] rrsagent, generate minutes