Search Results for author: Mohammad Mahmoudi

Found 4 papers, 1 papers with code

Fast and Optimal Adaptive Tracking Control: A Novel Meta-Reinforcement Learning via Conditional Generative Adversarial Net

no code implementations24 Jun 2022 Mohammad Mahmoudi, Nasser Sadati

Then, we introduce a novel meta-reinforcement learning framework to adapt the latent space of CGAN to the system's uncertainties as an optimal direct adaptive controller without any system identifier.

Meta Reinforcement Learning

SLTEV: Comprehensive Evaluation of Spoken Language Translation

1 code implementation EACL 2021 Ebrahim Ansari, Ond{\v{r}}ej Bojar, Barry Haddow, Mohammad Mahmoudi

SLTev reports the quality, latency, and stability of an SLT candidate output based on the time-stamped transcript and reference translation into a target language.

Machine Translation Translation

Supervised Morphological Segmentation Using Rich Annotated Lexicon

no code implementations RANLP 2019 Ebrahim Ansari, Zden{\v{e}}k {\v{Z}}abokrtsk{\'y}, Mohammad Mahmoudi, Hamid Haghdoost, Jon{\'a}{\v{s}} Vidra

In the experimental phase, using the hand-annotated Persian lexicon and two smaller similar lexicons for Czech and Finnish languages, we evaluated the effect of the training data size, different hyper-parameters settings as well as different RNN-based models.


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