Re: [Moses-support] EMS for the neural age?

Thanks Matt for the promotion! I’ve been using this ducttape workflow for about 6 months and is pretty happy with it. That’s why I thought it’s time to give it a bigger audience. I agree ducttape is a bit under-maintained at this moment (the core code is left there for ~4 years without any

Re: [Moses-support] EMS for the neural age?

W dniu 27.11.2017 o 11:19, Barry Haddow pisze: > > For the marian usage examples, I would go for the lowest common > denominator - shell scripts. Generally more readable than Makefiles. Good point. My needs for experimental set-ups does not necessarily overlap with readable tutorials.

Re: [Moses-support] EMS for the neural age?

Hi All I did produce a version of experiment.perl for Groundhog (remember that?) but it's not much use for any other nmt system. The problem (well actually the big advantage!) of nmt is that the pipeline is too simple for a tool like experiment.perl. And the experiments that do need tool

Re: [Moses-support] EMS for the neural age?

I can really recommend Eman to people interested in spawning dozens of similar experiments, by deriving new variations from older ones. Eman will take care of reusing reusable bits and creating new bits as needed. So e.g. corpus preprocessing, bpe etc. could be reused when you want to try new

Re: [Moses-support] EMS for the neural age?

This looks good. OK, I guess ducttape it is. W dniu 26.11.2017 o 14:56, Matt Post pisze: > Shuoyang Ding put this together recently: > > https://github.com/shuoyangd/tape4nmt > > matt > > >> On Nov 26, 2017, at 2:31 PM, Marcin Junczys-Dowmunt >> wrote: >> >> Hi Ondrej,

Re: [Moses-support] EMS for the neural age?

Shuoyang Ding put this together recently: https://github.com/shuoyangd/tape4nmt matt > On Nov 26, 2017, at 2:31 PM, Marcin Junczys-Dowmunt > wrote: > > Hi Ondrej, > you do not seem confident enough to recommend Eman :) > > I now took another look at duct tape.

Re: [Moses-support] EMS for the neural age?

Hi Ondrej, you do not seem confident enough to recommend Eman :) I now took another look at duct tape. That does not look too bad, basically Make with multi-targets and easier reuse of existing recipes (which is a nightmare in GNU make). Is anyone still using duct tape, commit dates are from

Re: [Moses-support] EMS for the neural age?

Hi Ergun, Thank you for answer. However, for clarification, I am well aware how to do preprocessing (and it's still evil :) ), that's not my point. I am just asking whether we have now some smarter tools around that help with the experimental setup and management, for instance for better

Re: [Moses-support] EMS for the neural age?

Hi, Marcin. I am afraid you are correct. I have my Eman and a couple of my students are using it (we have Neural Monkey, Nematus, t2t and probably already also Marian in), but it has a rather steep learning curve and it generally has other bells and whistles that what someone with data and

Re: [Moses-support] EMS for the neural age?

Dear Marcin, I have uploaded my EMS files for WMT'16: https://github.com/bicici/ParFDAWMT16 Text processing steps can be language-dependent, might require domain knowledge and expertise, and distinct you from others elevating your results. I suggest reading relevant sections from the papers of

[Moses-support] EMS for the neural age?

Hi list, I am preparing a couple of usage example for my NMT toolkit and got hung up on all the preprocessing and other evil stuff. I am wondering is there now anything decent around for doing preprocessing, running experiments and evaluation? Or is the best thing still GNU make (isn't that