Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Kalaidin, Pavel"'
Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text generation output
Externí odkaz:
http://arxiv.org/abs/2101.04229
Toxicity has become a grave problem for many online communities and has been growing across many languages, including Russian. Hate speech creates an environment of intimidation, discrimination, and may even incite some real-world violence. Both rese
Externí odkaz:
http://arxiv.org/abs/2010.11666
In this work, we present a novel approach for simultaneous knowledge transfer and model compression called Weight Squeezing. With this method, we perform knowledge transfer from a teacher model by learning the mapping from its weights to smaller stud
Externí odkaz:
http://arxiv.org/abs/2010.06993
Headline generation is a special type of text summarization task. While the amount of available training data for this task is almost unlimited, it still remains challenging, as learning to generate headlines for news articles implies that the model
Externí odkaz:
http://arxiv.org/abs/1901.07786
Autor:
Trusov, Roman, Natekin, Alexey, Kalaidin, Pavel, Ovcharenko, Sergey, Knoll, Alois, Fazylova, Aida
Publikováno v:
2015 Artificial Intelligence & Natural Language & Information Extraction, Social Media & Web Search FRUCT Conference (AINL-ISMW FRUCT); 2015, p110-117, 8p
