Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Michael White

Michael White

6 paper cards in Mova's library · 2002–2016

Michael White wrote 6 of the papers Mova reads, in 2002–2016, most of them on Machine translation, Universal Dependencies, Part-of-speech tagging; often with Rajakrishnan Rajkumar, Amanda Stent, Anja Belz.

OpenAlex · ORCID · h-index 35 · 12011 citations · 223 works — openalex, 2026-10-18

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology · ORCID

Topics: Machine translation 6 · Universal Dependencies 1 · Part-of-speech tagging 1

Papers

  1. Enhancing PTB Universal Dependencies for Grammar-Based Surface Realization (2016)
    Grammar-based realisers work well when their input carries long-distance dependencies and coordination, but standard UD conversions from the Penn Treebank lose these, because the conversion ignores the traces.
  2. The First Surface Realisation Shared Task: Overview and Evaluation Results (2011)
    The paper reports the first surface realisation shared task. Teams received a common input (a shallow track and a deep track, both derived from Penn Treebank parses) and produced English sentences. Five teams submitted six systems, and the corpus sentences were scored as a human topline. Systems were judged…
  3. Linguistically Motivated Complementizer Choice in Surface Realization (2011)
    The optional complementizer "that" (as in "he said that ...") is left out in about two thirds of Penn Treebank cases, and its presence changes fluency and sometimes meaning.
  4. A More Precise Analysis of Punctuation for Broad-Coverage Surface Realization with CCG (2008)
    The paper gives punctuation a lexical analysis in a broad-coverage CCG realisation grammar. In CCGbank, punctuation marks carry categories taken from their tags and sit inside binary rules, which is enough for parsing but overgenerates in realisation: a comma category can wrap a sentence in commas or repeat itself.…
  5. Towards broad coverage surface realization with CCG (2007)
    A progress report on the first broad-coverage English surface realiser for Combinatory Categorial Grammar, built on OpenCCG.
  6. Learning Domain-Specific Transfer Rules: An Experiment with Korean to English Translation (2002)
    An MT system that learns lexico-structural transfer rules from parsed bitexts, for domain-specific Korean-to-English translation.

Co-authors (10)

This page in Markdown → https://md.mova.elamur.ai/free/en/docs/papers/authors/michael-white/