I am looking for a way to extract the potential subject and object from a question in French.

For the moment, I am building some handmade rules. Alternatively, I started to think of using an already trained model for the task. I wanted to use StanfordNLP parser but unfortunately it is not free for commercial use.

So, here comes the questions:

  1. Are they ML models used for this task?

  2. Are they labeled data sets (in french) which can help create ML models used for this task?

[Edit] I am looking mainly for open source tools/ libraries.

Google SyntaxNe has pre-trained models for French. It is open source and can be customized for a specific use-case.

https://github.com/tensorflow/models/blob/master/research/syntaxnet/g3doc/universal.md

With this, you can create a dependency tree for questions and evaluate fitness for this application.

Your Answer

By clicking "Post Your Answer", you acknowledge that you have read our updated terms of service, privacy policy and cookie policy, and that your continued use of the website is subject to these policies.

Not the answer you're looking for? Browse other questions tagged or ask your own question.