Allan Jie

icon indicating a website link https://allanj.github.io icon indicating an email [email protected]

icon company Salesforce Research icon location Singapore icon location NLP Scientist at AI Lab, ByteDance, Singapore. Ph.D. from SUTD. Working on Semantic parsing, Dependency parsing and Named Entity Recognition

Results 40 comments of Allan Jie

Is it possible to use TemporalConvolution with masking?

Anyone has solution on this

I don't know how to run your code

or you can copy the command out of the "bash" file to run? For example, ``` python3 xxx ``` But I doubt that Google Colab can host for a long...

I don't know how to run your code

Usually, you should be able to directly run this in the terminal (in your server). ``` bash scripts/run_math23k.sh ```

I don't know how to run your code

Would be good if you can let me know the errors after you run the command ``` bash scripts/run_math23k.sh ``` In google colab, probably things will be different, I might...

Cannot run your training code

Sure. For the MAWPS dataset, we only conduct the 5-fold cross-validation experiments in the paper. Thus, I didn't upload the train/test splits for MAWPS. So maybe you can run the...

Cannot run your training code

Sure. Here comes the five-fold data: https://drive.google.com/file/d/1oQZUPeIA6TlNySqjcZhTMQA4-onwljTU/view?usp=sharing. I didn't upload it to GitHub as it is a bit large for GitHub.

Thanks for the'hard method', when will you relase the soft version ?

I'm on holiday at the moment and will finish it probably by 24 Sept. In the meanwhile, if you need to run the implementation immediately, you can check out the...

Thanks for the'hard method', when will you relase the soft version ?

Hi @hvingelby , I'm still in the middle of the integration. The early ACL deadline this year prevents me from doing so in a short time. But I will definitely...

Thanks for the'hard method', when will you relase the soft version ?

Guys, sorry for the pretty delayed late response. The soft version will be released by the end of this week. Thanks 🙂

Thanks for the'hard method', when will you relase the soft version ?

Though I haven't released yet, I want to let you guys know that I have implemented the `soft` variant in the [adding-soft-model](https://github.com/allanj/ner_incomplete_annotation/tree/adding-soft-model) branch for which you might want to check...