Russian Inappropriate Messages

🚀 Russian Inappropriate Messages Classification Model

This model is designed to detect inappropriate messages in the Russian language. It focuses on a derivative of toxicity, providing an additional layer of filtering after toxicity and obscenity checks.

🚀 Quick Start

The 'inappropriateness' concept in this model is not a substitute for toxicity but a derivative of it. The model can serve as an additional layer of inappropriateness filtering after toxicity and obscenity filtration. You can detect the exact sensitive topic by using another model. The proposed pipeline is shown in the scheme below.

You can also train one classifier for both toxicity and inappropriateness detection. The data to be mixed with toxic labelled samples could be found on our GitHub or on kaggle

✨ Features

Inappropraiteness Intuition

This model is trained on a dataset of inappropriate Russian messages. An inappropriate utterance generally has no obscene words or toxic intent but can harm the speaker's reputation. Find some sample for more intuition in the table below. Learn more about the concept of inappropriateness in this article presented at the workshop for Balto - Slavic NLP at the EACL - 2021 conference. Note that this article describes the first version of the dataset, while the model is trained on the extended version available on our GitHub or on kaggle. The dataset properties are the same as described in the article, only the size differs.

Metrics

The model was trained, validated, and tested only on samples with 100% confidence, achieving the following metrics on the test set:

📄 License

This project is licensed under the [Creative Commons Attribution - NonCommercial - ShareAlike 4.0 International License][cc - by - nc - sa].

[![CC BY - NC - SA 4.0][cc - by - nc - sa - image]][cc - by - nc - sa]

[cc - by - nc - sa]: http://creativecommons.org/licenses/by - nc - sa/4.0/ [cc - by - nc - sa - image]: https://i.creativecommons.org/l/by - nc - sa/4.0/88x31.png

📚 Documentation

Citation

If you find this repository helpful, feel free to cite our publication:

@inproceedings{babakov-etal-2021-detecting,
    title = "Detecting Inappropriate Messages on Sensitive Topics that Could Harm a Company{'}s Reputation",
    author = "Babakov, Nikolay  and
      Logacheva, Varvara  and
      Kozlova, Olga  and
      Semenov, Nikita  and
      Panchenko, Alexander",
    booktitle = "Proceedings of the 8th Workshop on Balto - Slavic Natural Language Processing",
    month = apr,
    year = "2021",
    address = "Kiyv, Ukraine",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2021.bsnlp-1.4",
    pages = "26--36",
    abstract = "Not all topics are equally {``}flammable{''} in terms of toxicity: a calm discussion of turtles or fishing less often fuels inappropriate toxic dialogues than a discussion of politics or sexual minorities. We define a set of sensitive topics that can yield inappropriate and toxic messages and describe the methodology of collecting and labelling a dataset for appropriateness. While toxicity in user - generated data is well - studied, we aim at defining a more fine - grained notion of inappropriateness. The core of inappropriateness is that it can harm the reputation of a speaker. This is different from toxicity in two respects: (i) inappropriateness is topic - related, and (ii) inappropriate message is not toxic but still unacceptable. We collect and release two datasets for Russian: a topic - labelled dataset and an appropriateness - labelled dataset. We also release pre - trained classification models trained on this data.",
}

📞 Contacts

If you have any questions please contact Nikolay