Romi121/particle_prediction_model

Japanese Particle Prediction Model

BERT based Token Classification model based on tohoku-nlp/bert-base-japanse and trained to predict a Japanese sentence with subject MASKed which particle (は,が,も) would most likely follow the MASK.

Model Use

This model was trained as part of a bigger project to predict implicit subjects in Japanese text. You can find whole project here [https://github.com/Romi212/Japanese-Subject-Predictor-System]

Training Details

Training Data

Model was trained using dataset https://github.com/UniversalDependencies/UD_Japanese-GSDLUW

The dataset was reduced only to sentences with a subject, and the subject subclause was replaced by [MASK] saving the particle asociated as the label to predict.