Contextual handling in neural machine translation: look behind, ahead and on both sides

• Autores: Ruchit Agrawal, Marco Turchi, Matteo Negri
• Localización: Proceedings of the 21st Annual Conference of the European Association for Machine Translation: 28-30 May 2018, Universitat d'Alacant, Alacant, Spain / coord. por Juan Antonio Pérez Ortiz, Felipe Sánchez Martínez, Miquel Esplà Gomis, Maja Popovic, Celia Rico Pérez, André Martins, Joachim Van den Bogaert, Mikel L. Forcada Zubizarreta, 2018, ISBN 978-84-09-01901-4, págs. 11-20
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • A salient feature of Neural Machine Translation (NMT) is the end-to-end nature of training employed, eschewing the need of separate components to model different linguistic phenomena. Rather, an NMT model learns to translate individual sentences from the labeled data itself. However, traditional NMT methods trained on large parallel corpora with a one-to-one sentence mapping make an implicit assumption of sentence independence. This makes it challenging for current NMT systems to model inter-sentential discourse phenomena. While recent research in this direction mainly leverages a single previous source sentence to model discourse, this paper proposes the incorporation of a context window spanning previous as well as next sentences as source-side context and previously generated output as target-side context, using an effective non-recurrent architecture based on self-attention. Experiments show improvement over non-contextual models as well as contextual methods using only previous context.