Dominik Macháček

Promoting the Knowledge of Source Syntax in Transformer NMT Is Not Needed

2019 · Institute of Formal and Applied Linguistics (ÚFAL)

The utility of linguistic annotation in neural machine translation seemed to had been established in past papers. The experiments were however limited to recurrent sequence-to-sequence architectures and relatively small data settings.\n\nWe focus on the state-of-the-art …