Allennlp: Can we use the allennlp for the other language, such as Dari, I want to implement the Coreference Resolution

[ghezalahmad]

Is your feature request related to a problem? Please describe.
A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]

Describe the solution you'd like
A clear and concise description of what you want to happen.

Describe alternatives you've considered
A clear and concise description of any alternative solutions or features you've considered.

Additional context
Add any other context or screenshots about the feature request here.

[matt-gardner]

Yes, you can train a coreference resolution model on another language. Nothing in allennlp is language-specific, except the inputs that you give it (e.g., your tokenizer, your training data). The tricky part is getting data and preprocessing in the language you care about. I suspect you'll have a hard time getting coreference resolution data for Dari.

[ghezalahmad]

Can you write me down the steps, as I developed already for the Dari language the following task, tokenization, sentence segmentation, part of speech tagging, NER, and also I annotated the corpus for the coreference resolution based on MUC6. Just if you kindly let me know the process or the steps need to implement.

[matt-gardner]

We have models available for tagging (POS, NER) and coref. You can train them on your data without writing any code if you get your data into the right format. You can learn about how to train an existing model on your own data by following our tutorials (particularly this one), and you can see the data format by looking at the dataset readers.

For tokenization and sentence segmentation, you'll have to write your own model for that.

[devajith]

is it applicable for 'Machine Comprehension' too ? any reference or tutorials ?