1- If the paper present translating between less-resources closely related languages then we have to provide proof that MT between related languages is easier for all systems (and provide citations) and so the current approach tests the new system on closely related languages.
2- Regarding of comparing apertium with corpus based systems, as you know for that we have to use some parallel data for training and testing systems. Previously I sued data form OPUS but their data has a lot of problems such as more than half of sentences were repeated and most of target sentence was unrelated to the source sentence..etc. So what I did I trained the systems with OPUS and tested it with my test data. I did the evaluation by comparing it with post-edited my test data. However the reviewers complain for bais and say it is not fair. so I want to know the others how they did it. And also if there is recently published papers about comparing NMT and apertium could you give us the link. 3- I think it will be great idea "something about all the technological improvements" as Flammie pointed out. We may do something like that section for each module with diagram explain its process by applying it for one pair. Sevilay On Wed, Oct 23, 2019 at 5:39 PM Juan Pablo <jpm...@unizar.es> wrote: > Same here! > I think submitting a paper to this Special Issue it is a great idea, as > coverage for low-resource languages is one of the distinctive traits of > Apertium as well as of this community. > If there is something I can contribute, I would be happy to collaborate in > it (no need to be in the authors' list). Please, keep me informed. > Best, > Juan Pablo > On 23/10/2019 13:36, Hèctor Alòs i Font wrote: > > Missatge de Tommi A Pirinen <tommi.antero.piri...@uni-hamburg.de> del dia > dc., 23 d’oct. 2019 a les 14:16: > >> On Mon, Oct 21, 2019 at 10:57:28PM +0300, Sevilay Bayatlı wrote: >> > Hi, >> > its my pleasure to participate too, if you want I can prepare the >> overleaf >> > and send it to you. But first lets discuss here the content of the >> paper. >> >> Ok. I have two things in mind that could be included: >> >> * some kind of description of all low-resource languages done in past 10 >> years, most of these have publications to cite etc. >> * something about all the technological improvements, all the gsoc >> stuffs that's been used now, etc. >> >> Some of the publications e.g. in loresmt this year also have really nice >> comparison between apertium and state-of-the-art NMT that should be >> replicated in this article. >> >> > If the article deals in a relevant way with Apertium and low-ressource > languages in recent years, I would be happy to collaborate in it. If it's > about technical issues, I can't contribute anything of interest. > > Hèctor > > > _______________________________________________ > Apertium-stuff mailing > listApertium-stuff@lists.sourceforge.nethttps://lists.sourceforge.net/lists/listinfo/apertium-stuff > > _______________________________________________ > Apertium-stuff mailing list > Apertium-stuff@lists.sourceforge.net > https://lists.sourceforge.net/lists/listinfo/apertium-stuff >
_______________________________________________ Apertium-stuff mailing list Apertium-stuff@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/apertium-stuff
