Command Palette
Search for a command to run...
Event2Mind for Russian: Understanding Emotions and Intents in Texts. Corpus and Model for Evaluation
{Tabisheva A. O Mironenko F. D. Filipetskaya D. V. Tikhonova M. I. Fenogenova A. S.}
Abstract
The paper provides a comprehensive overview of the corpus for the Russian language for the commonsense inference task. Namely, we construct event phrases, which cover a wide range of everyday situations with labelled intents and reactions of the event main participant and emotions of other people involved. The dataset consists of two parts: a crowdsourced corpus of 6,756 examples from Russian sources and a translated into Russian part of the original corpus of 23,409 examples. Apart from this, we use the collected data in order to train the event2mind model for the Russian language. The paper presents careful description of the best Russian model and the results of the conducted experiments.
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| common-sense-reasoning-on-russian-event2mind | ruscorpora fasttext + GRU | recall@10: 0.822 |
| common-sense-reasoning-on-russian-event2mind | ruscorpora fasttext + LSTM | recall@10: 0.821 |
| common-sense-reasoning-on-russian-event2mind | araneum fasttext + LSTM | recall@10: 0.818 |
| common-sense-reasoning-on-russian-event2mind | araneum word2vec (skipgram) + LSTM | recall@10: 0.816 |
| common-sense-reasoning-on-russian-event2mind | ruscorpora word2vec (skipgram) + GRU | recall@10: 0.825 |
| common-sense-reasoning-on-russian-event2mind | araneum fasttext + GRU | recall@10: 0.819 |
| common-sense-reasoning-on-russian-event2mind | araneum word2vec (skipgram) + GRU | recall@10: 0.827 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.