@article{improvingasequencetosequencenlpmodel,
  title = {Improving a sequence-to-sequence nlp model using a reinforcement learning policy algorithm},
  author = {Jabri Ismail and Aboulbichr Ahmed and El ouaazizi Aziza},
  year = {2022},
  eprint = {2212.14117},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2212.14117v1},
}