[Mova](https://md.mova.elamur.ai/free/en/) · [this page in HTML](https://mova.elamur.ai/free/en/docs/papers/authors/qun-liu/)

[home](https://md.mova.elamur.ai/free/en/) / [docs](https://md.mova.elamur.ai/free/en/docs/) / [papers](https://md.mova.elamur.ai/free/en/docs/papers/) / [authors](https://md.mova.elamur.ai/free/en/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](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/); often with [Shouxun Lin](https://md.mova.elamur.ai/free/en/docs/papers/authors/shouxun-lin/), Haitao Mi, Hui Yu.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Qun+Liu) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Qun+Liu) · [dblp](https://dblp.org/search?q=Qun+Liu) · [ACL Anthology](https://aclanthology.org/search/?q=Qun+Liu) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Qun+Liu)

Topics: [Machine translation](https://md.mova.elamur.ai/free/en/docs/papers/topics/machine-translation/) 3

## Papers

1. **[RED: A Reference Dependency Based MT Evaluation Metric](https://md.mova.elamur.ai/free/en/docs/papers/yu-2014-red-reference-dependency-based-mt/)** *(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](https://md.mova.elamur.ai/free/en/docs/papers/mi-2008-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](https://md.mova.elamur.ai/free/en/docs/papers/liu-2006-tree-string-alignment-template-statistical/)** *(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)

- [Shouxun Lin](https://md.mova.elamur.ai/free/en/docs/papers/authors/shouxun-lin/) ×2
- Haitao Mi
- Hui Yu
- Jun Xie
- [Liang Huang](https://md.mova.elamur.ai/free/en/docs/papers/authors/liang-huang/)
- [Wenbin Jiang](https://md.mova.elamur.ai/free/en/docs/papers/authors/wenbin-jiang/)
- Xiaofeng Wu
- [Yang Liu](https://md.mova.elamur.ai/free/en/docs/papers/authors/yang-liu/)
- [← previous Qiang Ning](https://md.mova.elamur.ai/free/en/docs/papers/authors/qiang-ning/)
- [next → R. Thomas McCoy](https://md.mova.elamur.ai/free/en/docs/papers/authors/r-thomas-mccoy/)
- [↑ back to Authors](https://md.mova.elamur.ai/free/en/docs/papers/authors/)