Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective

Documenti analoghi

• Seq2Seq2Seq: Lossless Data Compression via Discrete Latent Transformers and Reinforcement Learning
  di: Khodabandeh, Mahdi, et al.
  Pubblicazione: (2026)
• Exploiting the Potential of Seq2Seq Models as Robust Few-Shot Learners
  di: Lee, Jihyeon, et al.
  Pubblicazione: (2023)
• Leveraging Graph Structure in Seq2Seq Models for Knowledge Graph Link Prediction
  di: Phuc, Luu Huu, et al.
  Pubblicazione: (2026)
• SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translation
  di: Xu, Ting, et al.
  Pubblicazione: (2025)
• Improving Bangla Linguistics: Advanced LSTM, Bi-LSTM, and Seq2Seq Models for Translating Sylheti to Modern Bangla
  di: Das, Sourav Kumar, et al.
  Pubblicazione: (2025)