Skoltech/russian-sensitive-topics

The concept of sensitive topics is described in this article presented at the workshop for Balto-Slavic NLP at the EACL-2021 conference . The model predicts combinations of 18 sensitive topics described in the article . The dataset is open-sourced on our GitHub or on kaggle . We tested the performance of the classifier only on the part of the manually labeled data that is why some topics are not well represented in the test set . You can find step-by-step instructions for using the model here . The data is the same as the original version of the dataset described in our article, the only difference is the size of the size . We are using the,