Topics of interest include, but are not limited to:

  • Theoretic study of challenges, opportunities, pros and cons of exploring semantics in SMT
  • Linguistic semantics for Semantics-driven SMT
    • Lexical semantics, e.g., word sense disambiguation/induction, semantic roles
    • Compositional semantics
    • Linguistically-motivated representations of sentences in the context of SMT
    • Discourse semantics, e.g., cohesion, coherence, discourse relation
  • Distributional semantics for Semantics-driven SMT
    • Distributional lexical/compositional/sentential representations
    • Models and algorithms for learning bilingual/multilingual distributional semantics
    • Distributional approaches to compositional semantics for the purpose of SMT
    • Deep learning approaches to distributional-semantics-driven SMT
  • Semantic knowledge for Semantics-driven SMT
    • Applications of multilingual ontology or knowledge bases in semantics-driven SMT
    • Learning and extracting multilingual semantic knowledge for translation
  • Semantically motivated evaluation for SMT