Format Novel Data

[bob-rietveld]

Thanks you for releasing your code. I have been able to train a model using my own dataset. I now want to use the trained model to predict unseen data. My question is what format should the data have (which does not have any annotations), and what flags should I set when only doing predictions using a trained model?

Thanks very much, Best

[lixin4ever]

This feature will be released soon, please stay tuned

[bob-rietveld]

Thanks very much, please let me know if I can be of assistance in testing / documentation etc.

[lixin4ever]

If you think the documentation can be refined, feel free to create a pull request.

As for the code handling incoming / unseen data, I am trying to finish the first version. After the first version is released, you can add comments or PR (if you want).

[bob-rietveld]

Hi, Any news, perhaps on making predictions? Thanks. By the way, I used your model in a Google Colab, be happy to share if that is something you are interested in. Best.

[lixin4ever]

This feature will be available soon (maybe after EMNLP 2019).

[bob-rietveld]

OK, thanks for the update.

[lixin4ever]

@good-marketing The new feature is available now. You can check work.py.

[bob-rietveld]

Very Nice, thanks. I'll see if I can get it working on my dataset this week!

[gnmarten]

@good-marketing I'd be interested in having a look at your Colab, thx in advance

[youyouyou404]

@good-marketing Hi, can you tell me how you annotate your data set? Thanks

[aurora1625]

@good-marketing Do you mind sharing your Colab notebook? Thanks!

[yassmine-lam]

@good-marketing I'd be interested in having a look at your Colab, thx in advance

Hi the same question plz thank u in advance