mhueppe / machineLearningProject_jaNoMi

This is a public Repository to manage the Machine Learning Project for WS 2024/25.
GNU General Public License v3.0
1 stars 0 forks source link

Find good model / method for NER (named entity recognition) for scientific texts #13

Open nllink opened 1 week ago

nllink commented 1 week ago

the basic spacy model for English language performs bad on our dataset. We need to find a better solution to automate the language engineering.

Possible candidates: SciSpacy: https://allenai.github.io/scispacy/ spaCy's Transformer-Based Models (en_core_web_trf)