This is about dependency parsing. The operation set of a shift-reduce parser was changed so that an arc is added as early as possible. It's claimed that "the longer a word has to wait to get assigned its head, the more opportunities there are for something to go awry." Why?

  • 1
    This isn’t a problem of dependency grammar but of a particular algorithm. In general, only non-deterministic parsing can be accurate. The rule you mention is just an heuristic so it’s basically empirical.
    – Atamiri
    May 6 '20 at 8:18

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.