no code implementations • Proceedings of the International Conference “Dialogue 2020” 2020 • Konovalov V. P., Gulyaev P. A., Sorokin A. A., Kuratov Y. M., Burtsev M. S.
Multilingual BERT has been shown to generalize well in a zero-shot cross-lingual setting.
3 code implementations • Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2019” 2019 • Baymurzina D. R., Kuznetsov D. P., Burtsev M. S.
In this paper we introduce pre-trained Russian language models which are used to extract embeddings (ELMo) to improve accuracy for classification of short conversational texts.
no code implementations • Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialogue 2019” 2019 • Le T. A., Petrov M. A., Kuratov Y. M., Burtsev M. S.
Coreference Resolution (CR) is one of the most difficult tasks in the field of Natural Language Processing due to the lack of deeply and comprehensively understanding the semantic meaning of the mention in not only the sentence-level context but also the entire document-level context.