Көптілді аударма моделі
Related Papers
GTCOM Neural Machine Translation Systems for WMT21
AbstractThis paper describes the Global Tone Communication Co., Ltd.’s submission of the WMT21 shared news translation task. We participate in six directions: English to/from Hausa, Hindi to/from Bengali and Zulu …...
Entropy-Based Vocabulary Substitution for Incremental Learning in Multilingual Neural Machine Translation
AbstractIn a practical real-world scenario, the longstanding goal is that a universal multilingual translation model can be incrementally updated when new language pairs arrive. Specifically, the initial vocabulary only covers …...
GTCOM Neural Machine Translation Systems for WMT22
AbstractGTCOM participates in five directions: English to/from Ukrainian, Ukrainian to/from Czech, English to Chinese and English to Croatian. Our submitted systems are unconstrained and focus on backtranslation, multilingual translation model …...
Pivot Translation for Zero-resource Language Pairs Based on a Multilingual Pretrained Model
AbstractA multilingual translation model enables a single model to handle multiple languages. However, the translation qualities of unlearned language pairs (i.e., zero-shot translation qualities) are still poor. By contrast, pivot …...