Search Results for author: Pavel Kalaidin

Found 4 papers, 1 papers with code

Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning

1 code implementation EACL 2021 Evgeny Lagutin, Daniil Gavrilov, Pavel Kalaidin

Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019).

Language Modelling reinforcement-learning +2

Reducing Unintended Identity Bias in Russian Hate Speech Detection

no code implementations EMNLP (ALW) 2020 Nadezhda Zueva, Madina Kabirova, Pavel Kalaidin

Toxicity has become a grave problem for many online communities and has been growing across many languages, including Russian.

Hate Speech Detection

Weight Squeezing: Reparameterization for Knowledge Transfer and Model Compression

no code implementations14 Oct 2020 Artem Chumachenko, Daniil Gavrilov, Nikita Balagansky, Pavel Kalaidin

We also proposed a variant of Weight Squeezing called Gated Weight Squeezing, for which we combined fine-tuning of BERT-Medium model and learning mapping from BERT-Base weights.

General Classification Model Compression +3

Cannot find the paper you are looking for? You can Submit a new open access paper.