Assessing the Importance of Frequency versus Compositionality for Subword-based Tokenization in NMT

Documenti analoghi

• Don't Rank, Combine! Combining Machine Translation Hypotheses Using Quality Estimation
  di: Vernikos, Giorgos, et al.
  Pubblicazione: (2024)
• Can the Variation of Model Weights be used as a Criterion for Self-Paced Multilingual NMT?
  di: Atrio, Àlex R., et al.
  Pubblicazione: (2024)
• Optimizing the Training Schedule of Multilingual NMT using Reinforcement Learning
  di: Allemann, Alexis, et al.
  Pubblicazione: (2024)
• NMT-Obfuscator Attack: Ignore a sentence in translation with only one word
  di: Sadrizadeh, Sahar, et al.
  Pubblicazione: (2024)
• Conversational Agents and the Understanding of Human Language: Reflections on AI, LLMs, and Cognitive Science
  di: Popescu-Belis, Andrei
  Pubblicazione: (2026)