structural-transformer icon indicating copy to clipboard operation
structural-transformer copied to clipboard

Inconsistent examples

Open goodbai-nlp opened this issue 6 years ago • 2 comments

Hi,

I am trying to reproduce the results of the baseline NMT system in your paper, however, I found the examples given in Readme and that in corpus_example are not consistent. (e.g. different from the example in Readme, the :wiki link here is not removed, even BPE has been applied).

Now I'm confused about which one I should follow, any suggestions :)?

goodbai-nlp avatar Sep 16 '19 03:09 goodbai-nlp

font{
    line-height: 1.6;
}
ul,ol{
    padding-left: 20px;
    list-style-position: inside;
}



First, you need to linearize the AMR graph.  You can use konstas's script or song's script, because the final performance impact is not significant. After that, you need to do the BPE operation.








On 9/16/2019 11:32,xfbai<[email protected]> wrote: 

Hi, I am trying to reproduce the results of the baseline NMT system in your paper, however, I found the examples given in Readme and that in corpus_example are not consistent. (e.g. different from the example in Readme, the :wiki link here is not removed, even BPE has been applied). Now I'm confused about which one I should follow, any suggestions :)?

—You are receiving this because you are subscribed to this thread.Reply to this email directly, view it on GitHub, or mute the thread.

Amazing-J avatar Sep 16 '19 06:09 Amazing-J

Hi,

Thanks for your rapid reply, I'll try that.

| |

| |

| On 9/16/2019 14:34,Amazing-J[email protected] wrote:

font{ line-height: 1.6; } ul,ol{ padding-left: 20px; list-style-position: inside; }

First, you need to linearize the AMR graph. You can use konstas's script or song's script, because the final performance impact is not significant. After that, you need to do the BPE operation.

On 9/16/2019 11:32,xfbai[email protected] wrote:

Hi, I am trying to reproduce the results of the baseline NMT system in your paper, however, I found the examples given in Readme and that in corpus_example are not consistent. (e.g. different from the example in Readme, the :wiki link here is not removed, even BPE has been applied). Now I'm confused about which one I should follow, any suggestions :)?

—You are receiving this because you are subscribed to this thread.Reply to this email directly, view it on GitHub, or mute the thread.

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or mute the thread.

goodbai-nlp avatar Sep 16 '19 07:09 goodbai-nlp