Re: [94attendees] Recordings?

Mikael Abrahamsson <swmike@swm.pp.se> Fri, 13 November 2015 12:40 UTC

Return-Path: <swmike@swm.pp.se>
X-Original-To: 94attendees@ietfa.amsl.com
Delivered-To: 94attendees@ietfa.amsl.com
Received: from localhost (ietfa.amsl.com [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 113CB1A1AE6 for <94attendees@ietfa.amsl.com>; Fri, 13 Nov 2015 04:40:02 -0800 (PST)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -1.568
X-Spam-Level:
X-Spam-Status: No, score=-1.568 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, HELO_EQ_SE=0.35, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, TVD_PH_BODY_ACCOUNTS_PRE=2.393, T_RP_MATCHES_RCVD=-0.01] autolearn=ham
Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id S_60TB1iTMQn for <94attendees@ietfa.amsl.com>; Fri, 13 Nov 2015 04:40:00 -0800 (PST)
Received: from uplift.swm.pp.se (swm.pp.se [212.247.200.143]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 9932D1A1F1D for <94attendees@ietf.org>; Fri, 13 Nov 2015 04:39:30 -0800 (PST)
Received: by uplift.swm.pp.se (Postfix, from userid 501) id 18B95A2; Fri, 13 Nov 2015 13:39:28 +0100 (CET)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=swm.pp.se; s=mail; t=1447418368; bh=MUP2RvY5f4Z9WY7P6xB3Yd48XwgTs7p05e1eUDqwgW8=; h=Date:From:To:cc:Subject:In-Reply-To:References:From; b=T0N0AuSDTwpu5nwKhBHP1PMguSbPUES8n2OKOm2WKRTkS6Q7gD+Y5HQeVjUXrdiLr iJFcrpfhwDI07x3xT1/sYa/GmyMsl0XSXi+o8XxoOpaNghHxKuBzcptbmS//LUgjI4 Fh2alY5k1+klhudywRAAtG/H/k58JHUd6cTi86zc=
Received: from localhost (localhost [127.0.0.1]) by uplift.swm.pp.se (Postfix) with ESMTP id 0F3EDA1; Fri, 13 Nov 2015 13:39:28 +0100 (CET)
Date: Fri, 13 Nov 2015 13:39:28 +0100 (CET)
From: Mikael Abrahamsson <swmike@swm.pp.se>
To: Lou Berger <lberger@labn.net>
In-Reply-To: <15100b63580.2818.9b4188e636579690ba6c69f2c8a0f1fd@labn.net>
Message-ID: <alpine.DEB.2.02.1511131333060.24520@uplift.swm.pp.se>
References: <43FBAFF6-C484-4B70-A75A-2710FFA4D1DC@gmail.com> <0AD40D29-E6D3-41C3-A720-9C9489482EE1@gmail.com> <47989D60-36B4-451D-9403-E8435E1448DA@gmail.com> <B0E65D10-981D-4AE7-8B13-58D32E1F662A@gmail.com> <5644960E.3090701@cea.fr> <5644A1E4.6080609@meetecho.com> <5644C378.9070404@cea.fr> <5644CB04.2040609@meetecho.com> <F4417972-A7E4-4D3E-961D-1E652071102E@gmail.com> <15100b63580.2818.9b4188e636579690ba6c69f2c8a0f1fd@labn.net>
User-Agent: Alpine 2.02 (DEB 1266 2009-07-14)
Organization: People's Front Against WWW
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed
Archived-At: <http://mailarchive.ietf.org/arch/msg/94attendees/stIHqZkiW-5vCfm3GgiOzTQFjHg>
Cc: 94attendees@ietf.org, Tina TSOU <tinatsou6@gmail.com>, Meetecho IETF support <ietf@meetecho.com>
Subject: Re: [94attendees] Recordings?
X-BeenThere: 94attendees@ietf.org
X-Mailman-Version: 2.1.15
Precedence: list
List-Id: "Mailing list of IETF 94 attendees that have opted in on this list. " <94attendees.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/94attendees>, <mailto:94attendees-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/94attendees/>
List-Post: <mailto:94attendees@ietf.org>
List-Help: <mailto:94attendees-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/94attendees>, <mailto:94attendees-request@ietf.org?subject=subscribe>
X-List-Received-Date: Fri, 13 Nov 2015 12:40:02 -0000

On Fri, 13 Nov 2015, Lou Berger wrote:

> We tried an ad hoc / informal test from a different provider. It got a lot 
> right, but where it went wrong it ranged from humorous to offensive.  I 
> believe a more formal test is being investigated...

I attended a RIPE meeting a year ago. They had a person that translated in 
real time and had text on a big screen. I talked to that person, and she 
said that they had been working with RIPE for a long time and thus had 
learnt a lot of the acronyms in wide use.

Translation was not perfect, but still very impressive since it was done 
in real time with a high degree of accuracy.

So it might be feasible to retroactively translate sessions and the result 
could be published weeks/months after the meeting, but I'd imagine we're 
talking ballpark 100-500kUSD a year for this effort even taking into 
account that the effort could be aided by automatic translation, meeting 
minutes, recordings, jabber scribes etc to aid in the final human product.

Perhaps someone would be willing to sponsor some of this though, because 
from a machine learning perspective it might be valuable data for someone 
to improve the automatic translation service accuracy.

-- 
Mikael Abrahamsson    email: swmike@swm.pp.se