49 citations · 190 across the 36 of their papers we have counts for
3 papers · 1 filter
Char-RNN and Active Learning for Hashtag Segmentation
Taisiya Glushkova, Ekaterina Artemova
We explore the abilities of character recurrent neural network (char-RNN) for hashtag segmentation. Our approach to the task is the following: we generate synthetic training datase…
Sentence Embeddings for Russian NLU
Dmitry Popov, Alexander Pugachev, Polina Svyatokum +2
We investigate the performance of sentence embeddings models on several tasks for the Russian language. In our comparison, we include such tasks as multiple choice question answeri…
Multilingual Named Entity Recognition Using Pretrained Embeddings, Attention Mechanism and NCRF
Anton A. Emelyanov, Ekaterina Artemova
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 to…