Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Hermann Ney

Hermann Ney

3 paper cards in Mova's library · 2006–2016

Hermann Ney wrote 3 of the papers Mova reads, in 2006–2016, most of them on Machine translation; often with Adrià de Gispert, David Vilar, Deepa Gupta.

OpenAlex · h-index 94 · 48282 citations · 1461 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 3

Papers

  1. CharacTer: Translation Edit Rate on Character Level (2016)
    CharacTER is a translation edit rate computed on characters. It keeps the word-level phrase shift of TER, so a moved phrase costs something, but the edit distance after the shifts is a character-level Levenshtein distance, with spaces counted as characters. Shifting characters directly was about 44 times slower, so…
  2. Error Analysis of Statistical Machine Translation Output (2006)
    The paper gives a hand-built error typology for statistical MT output and applies it to the RWTH system in the first TC-STAR evaluation, for Spanish-to-English, English-to-Spanish and Chinese-to-English, on speech-derived data (clean text, verbatim transcripts and recogniser output).
  3. Morpho-syntactic Information for Automatic Error Analysis of Statistical Machine Translation Output (2006)
    The paper uses word classes to find out where an SMT system goes wrong, for Spanish and English in the TC-STAR parliament data.

Co-authors (13)

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