I am graduate student and I am doing a Master of Translation and interpretation Arabic English. I need to pursue study in machine translation but I do not know where exactly to start, NLP, computational linguistics . I have a slight knowledge of python. Thank you

1 Answer 1


There are two approaches to MT: rule-based and statistical. The former is “more linguistic” in the sense that it uses rules based on linguistic knowledge. This includes morphology (the lexicon), syntax (dealing with the hierarchy of sentences), semantics (the context-independent meaning of phrases) and pragmatics (the meaning with respect to context). The latter is more maths and CS as it requires extensive knowledge of probability, statistical models etc.

  • 1
    I'm not an expert in the field, but does anyone still work with rule-based machine translation (outside of academia)? My impression is that all "serious" MT tools and products have moved on to statistical MT years ago.
    – jick
    Commented May 10, 2020 at 21:19
  • @jick You’re right but from an academic perspective RBMT is still relevant and there are some new methods that might take root.
    – Atamiri
    Commented May 10, 2020 at 21:42

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.