Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Qun Liu

Qun Liu

3 paper cards in Mova's library · 2006–2014

Qun Liu wrote 3 of the papers Mova reads, in 2006–2014, most of them on Machine translation; often with Shouxun Lin, Haitao Mi, Hui Yu.

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

Topics: Machine translation 3

Papers

  1. RED: A Reference Dependency Based MT Evaluation Metric (2014)
    RED parses only the reference, never the hypothesis, so that parsing noise from the MT output does not enter the score.
  2. Forest-Based Translation (2008)
    Tree-based translation takes the 1-best parse of the source sentence as input. A parser error then becomes a translation error. The paper proposes decoding over a packed forest, a compact graph that holds exponentially many parses, instead of the single tree. A k-best list is shown to be a poor substitute: a 50-best…
  3. Tree-to-String Alignment Template for Statistical Machine Translation (2006)
    A tree-to-string alignment template (TAT) pairs a source parse subtree, with variables at some of its leaves, with a target string that uses the same variables.

Co-authors (8)

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