домен ішінде

This paper investigates adapting a lexicalized probabilistic context-free grammar (PCFG) to a novel domain, using maximum a posteriori (MAP) estimation. The MAP framework is gen- eral enough to include some …...

We describe a semantic role labeler with state- of-the-art performance and low computational requirements, which uses convolutional and time-domain neural networks. The system is designed to work with features derived …...

AbstractAdaptive Machine Translation purports to dynamically include user feedback to improve translation quality. In a post-editing scenario, user corrections of machine translation output are thus continuously incorporated into translation models, …...