W3C home > Mailing lists > Public > public-multilingualweb-lt@w3.org > January 2013

Re: Locworld June Re: Update [Agenda] MLW-LT call 7 January, 4 p.m. UTC

From: Tadej Štajner <tadej.stajner@ijs.si>
Date: Fri, 11 Jan 2013 10:40:15 +0100
Message-ID: <50EFDDFF.80501@ijs.si>
To: Serge Gladkoff <sgladkoff@logrus.ru>
CC: Felix Sasaki <fsasaki@w3.org>, Dave Lewis <dave.lewis@cs.tcd.ie>, "Dr. David Filip" <David.Filip@ul.ie>, Yves Savourel <ysavourel@enlaso.com>, "public-multilingualweb-lt@w3.org" <public-multilingualweb-lt@w3.org>
Hi, Serge, all,
if we're doing a second submission, here's how my part looks:

Contact: tadej.stajner@ijs.si
Bio: Tadej Štajner is a researcher at Jožef Stefan Institute, Ljubljana, 
Slovenia, performing research on natural language processing in 
multilingual and cross-lingual applications.
Topic: Creating translation context with disambiguation
Synopsis: Since short pieces of content can be difficult to interpret 
when placed out of context, we discuss and demonstrate the application 
of natural language processing techniques, such as word sense 
disambiguation, entity extraction and disambiguation for the purpose of 
annotating words, names and phrases with explicit identifiers, providing 
the needed additional context. We describe how the ITS2.0 standard 
supports this scenario, and how the same mechanism could be applied to 
improving machine translation quality and assisting the terminology 
management life cycle.

Let me know what would add, and I can make a second pass to make it more 
coherent Also, if no-one else is contributing, we can probably move the 
discussion off-list.
-- Tadej

On 11. 01. 2013 00:17, Serge Gladkoff wrote:
> Hi All,
> I have submitted a presentation proposal about WICS visualization, but it's narrow topic.
> I can do second submission tomorrow, and they will accept my submission past deadline (I will see to it), but I need a topic, the synopsis, and co-presenters contact data and bio.
> Regards,
> Serge Gladkoff
> -----Original Message-----
> From: Felix Sasaki [mailto:fsasaki@w3.org]
> Sent: Thursday, January 10, 2013 8:23 AM
> To: Tadej Štajner
> Cc: Dave Lewis; Dr. David Filip; Yves Savourel; public-multilingualweb-lt@w3.org
> Subject: Re: Locworld June Re: Update [Agenda] MLW-LT call 7 January, 4 p.m. UTC
> Thank you, Tadej, and thanks to all for this thread.
> the practical question is now who would be able to include Tadej in a submission. And the deadline is today, IIRC.
> Best,
> Felix
> Am 09.01.13 12:22, schrieb Tadej Štajner:
>> Hi, all,
>> while I can't commit to coming to LocWorld, I can contribute some
>> content to a submission on the disambiguation part, and make a demo
>> available.
>> -- Tadej
>> On 09. 01. 2013 02:28, Dave Lewis wrote:
>>> David,
>>> You are right, this sort of opportunistic MT use of disambiguation
>>> data would suit more the home spun/push button trained MT market, I'd
>>> presume the big guys like Google would have sucked DBpedia dry of all
>>> useful parallel text already.
>>> The other two use cases you describe are also very credible options,
>>> and probably more immediately understandable to localization folk so
>>> very worth pursuing.
>>> cheers,
>>> Dave
>>> On 08/01/2013 22:25, Dr. David Filip wrote:
>>>> Dave, says that the disambiguation is more useful for MT. I do not
>>>> entirely agree.
>>>> I do not see large MT providers like Google building support for
>>>> this info. On the other hand, SOLAS consumes the disambiguation info
>>>> and presents it to the human agent, as a color-coded span with
>>>> linked reference, eventually prose comment.
>>>> People keep talking about importance of terminology management,
>>>> however terminology has always lower priority compared to direct
>>>> leveraging, as it is harder to put a financial benefit tag on it.
>>>> Getting marked terminology candidates via ITS encoded disambiguation
>>>> info is very attractive bootstrapping scenario for human translation..
>>>> Apart from that using disambiguation as term candidates in a broder
>>>> term life cycle is an obvious backdoor for terminology (term), which
>>>> is good.
Received on Friday, 11 January 2013 09:41:55 UTC

This archive was generated by hypermail 2.4.0 : Friday, 17 January 2020 16:32:00 UTC