Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language

17 May 2019  ·  Yuri Kuratov, Mikhail Arkhipov ·

The paper introduces methods of adaptation of multilingual masked language models for a specific language. Pre-trained bidirectional language models show state-of-the-art performance on a wide range of tasks including reading comprehension, natural language inference, and sentiment analysis. At the moment there are two alternative approaches to train such models: monolingual and multilingual. While language specific models show superior performance, multilingual models allow to perform a transfer from one language to another and solve tasks for different languages simultaneously. This work shows that transfer learning from a multilingual model to monolingual model results in significant growth of performance on such tasks as reading comprehension, paraphrase detection, and sentiment analysis. Furthermore, multilingual initialization of monolingual model substantially reduces training time. Pre-trained models for the Russian language are open sourced.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Question Answering on SQuAD1.1 (Hardware Burden metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Sentiment Analysis RuSentiment RuBERT Weighted F1 72.63 # 3
Question Answering SQuAD1.1 RuBERT F1 84.6 # 101
Hardware Burden None # 1
Operations per network pass None # 1

Methods


No methods listed for this paper. Add relevant methods here