Two-stage approach in Russian named entity recognition

Mozharova, V. A.; Loukachevitch, Natalia

doi:10.1109/fruct.2016.7584769

Cited by 29 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We experimented with transfer learning from other NER corpora. We used three corpora as source for transfer: Russian NER corpus (Mozharova and Loukachevitch, 2016), Bulgarian BulTreeBank (Simov et al, 2004;Georgiev et al, 2009), and BSNLP 2017 Shared Task dataset (Piskorski et al, 2017) 6 with Czech, Russian, and Polish data. For pre-training we use stratified sample from the concatenated dataset.…”

Section: Resultsmentioning

confidence: 99%

Tuning Multilingual Transformers for Language-Specific Named Entity Recognition

Архипов

Трофимова²,

Kuratov

et al. 2019

Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing

104

View full text Add to dashboard Cite

Our paper addresses the problem of multilingual named entity recognition on the material of 4 languages: Russian, Bulgarian, Czech and Polish. We solve this task using the BERT model. We use a hundred languages multilingual model as base for transfer to the mentioned Slavic languages. Unsupervised pre-training of the BERT model on these 4 languages allows to significantly outperform baseline neural approaches and multilingual BERT. Additional improvement is achieved by extending BERT with a word-level CRF layer. Our system was submitted to BSNLP 2019 Shared Task on Multilingual Named Entity Recognition and took the 1st place in 3 competition metrics out of 4 we participated in. We open-sourced NER models and BERT model pre-trained on the four Slavic languages.

show abstract

Section: Resultsmentioning

confidence: 99%

Tuning Multilingual Transformers for Language-Specific Named Entity Recognition

Архипов

Трофимова²,

Kuratov

et al. 2019

Proceedings of the 7th Workshop on Balto-Slavic Natural Language Processing

104

View full text Add to dashboard Cite

show abstract

“…The proposed corpora to use are: English and Russian news corpora, CoNLL'03 (Tjong Kim Sang and De Meulder, 2003) and Persons-1000 (Mozharova and Loukachevitch, 2016) respectively, and French social media corpus CAp'2017 (Lopez et al, 2017).…”

Section: Methodsmentioning

confidence: 99%

Robust to Noise Models in Natural Language Processing Tasks

Malykh

2019

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

View full text Add to dashboard Cite

There are a lot of noisy texts surrounding a person in modern life. A traditional approach is to use spelling correction, yet the existing solutions are far from perfect. We propose a robust to noise word embeddings model which outperforms existing commonly used models like fasttext and word2vec in different tasks. In addition, we investigate the noise robustness of current models in different natural language processing tasks. We propose extensions for modern models in three downstream tasks, i.e. text classification, named entity recognition and aspect extraction, these extensions show improvement in noise robustness over existing solutions.

show abstract

“…To the best of our knowledge, several datasets for named entity recognition in the Russian language are available: the dataset, developed by Gareev et al [16], Persons 1000 and Collection 5 [30], [40], [42], FactRuEval 2016 [7], the Russian subset of the BSNLP Shared Task [33].…”

Section: Named Entity Recognition and Relation Extraction For The Rusmentioning

confidence: 99%

“…The results of experiments showed that CRF-based approach outperformed knowledge-based approach on 13% of F-measure. Mozharova and Loukachevitch investigated the knowledge and context features for the CRF model in the NER task [30].…”

Section: Named Entity Recognition and Relation Extraction For The Rusmentioning

confidence: 99%

Rurebus-2020 Shared Task: Russian Relation Extraction for Business

Ivanin¹,

Abbyy²,

Artemova³

et al. 2020

Computational Linguistics and Intellectual Technologies

View full text Add to dashboard Cite

In this paper, we present a shared task on core information extraction problems, named entity recognition and relation extraction. In contrast to popular shared tasks on related problems, we try to move away from strictly academic rigor and rather model a business case. As a source for textual data we choose the corpus of Russian strategic documents, which we annotated according to our own annotation scheme. To speed up the annotation process, we exploit various active learning techniques. In total we ended up with more than two hundred annotated documents. Thus we managed to create a high-quality data set in short time. The shared task consisted of three tracks, devoted to 1) named entity recognition, 2) relation extraction and 3) joint named entity recognition and relation extraction. We provided with the annotated texts as well as a set of unannotated texts, which could of been used in any way to improve solutions. In the paper we overview and compare solutions, submitted by the shared task participants. We release both raw and annotated corpora along with annotation guidelines, evaluation scripts and results at https://github.com/dialogue-evaluation/RuREBus.

show abstract

Two-stage approach in Russian named entity recognition

Cited by 29 publications

References 8 publications

Tuning Multilingual Transformers for Language-Specific Named Entity Recognition

Tuning Multilingual Transformers for Language-Specific Named Entity Recognition

Robust to Noise Models in Natural Language Processing Tasks

Rurebus-2020 Shared Task: Russian Relation Extraction for Business

Contact Info

Product

Resources

About