Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF

Emelyanov A.; E. Artemova

doi:10.18653/v1/W19-3713

Publications

?

Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF

P. 94–99.

Emelyanov A., Artemova E.

In this paper we tackle multilingual named entity recognition task. We use the BERT Language Model as embeddings with bidirectional recurrent network, attention, and NCRF on the top. We apply multilingual BERT only as embedder without any fine-tuning. We test out model on the dataset of the BSNLP shared task, which consists of texts in Bulgarian, Czech, Polish and Russian languages.

Keywords: BERT Language Model

Publication based on the results of:

Development of Mathematical Models and Methods for Recommender Systems and Natural Language Processing (2019)

In book

Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing, 2019, Florence, Italy, Association for Computational Linguistics

Association for Computational Linguistics, 2019.

Automatic generation of reviews of scientific papers

Nikiforovskaya A., Kapralov N., Vlasova A. et al., , in: 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA 2020).: Miami: IEEE, 2020. P. 314–319.

With an ever-increasing number of scientific papers published each year, it becomes more difficult for researchers to explore a field that they are not closely familiar with already. This greatly inhibits the potential for cross-disciplinary research. A traditional introduction into an area may come in the form of a review paper. However, not all areas ...

Added: December 28, 2020

RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark

Shavrina T., Fenogenova A., Emelyanov A. et al., , in: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).: Association for Computational Linguistics, 2020. P. 4717–4726.

Added: November 22, 2020

Gapping parsing using pretrained embeddings, attention mechanism and NCRF

Emelyanov A., Artemova E., , in: Computational Linguistics and Intellectual Technologies Papers from the Annual International Conference “Dialogue” (2019)Issue 18.: M.: Russian State University for the Humanitie, 2019. P. 203–212.

The article is devoted to the problem of automatic gapping resolution for the Russian language. We use BERT Language Model as embeddings with bidirectional recurrent net- work, attention, and NCRF on the top. Unlike other models these are using BERT, we apply BERT only as embedder without any fine-tuning. As a result, our implementation took ...

Added: October 29, 2020

RENERSANs: Relation Extraction and Named Entity Recognition as Sequence Annotation

Davletov A., Gordeev D., Rei A. et al., , in: Компьютерная лингвистика и интеллектуальные технологии: по материалам ежегодной международной конференции «Диалог» (Москва, 17–20 июня 2020 г.)Issue 19(26): дополнительный том.: -, 2020. P. 187–197.

In this work we present our system for RuREBus shared task held together with Dialog 2020 conference. The task consisted of 3 subtasks: named entity recognition, relation extraction with provided named entity tags and end-to-end relation extraction. Our system took the first and the second place in the first and the second subtasks respectively. For ...

Added: October 10, 2020

RuREBus-2020 Shared Task: Russian Relaton Extraction for Business

Artemova E., Batura T., Sarkisyan V. et al., , in: Компьютерная лингвистика и интеллектуальные технологии: По материалам ежегодной международной конференции «Диалог» (Москва, 17 июня — 20 июня 2020 г.)Вып. 19(26).: М.: Изд-во РГГУ, 2020. P. 416–432.

В статье представлены результаты соревнования по распознаванию именованных сущностей и извлечению отношений. Целью соревнования является сравнение методов извлечения сущностей и отношений на русском языке в постановке, приближенной к индустриальным задачам. В качестве исходной коллекции текстов использовался корпус Минэкономразвития РФ, содержащий программы стратегического развития. Корпус был размечен в соответствии с инструкцией, разработанной авторами статьи. В процессе ...

Added: June 11, 2020