Liang Huang

4 paper cards in Mova's library · 2006–2017

Liang Huang wrote 4 of the papers Mova reads, in 2006–2017, most of them on Machine translation, Discourse analysis, Treebanks; often with Aravind Joshi, Haitao Mi, Kai Zhao.

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

Papers

Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank (2017)
The paper proposes a discourse parser that builds constituency and RST discourse trees in one pass, with no pre-segmentation and no external syntactic features.
Structured Perceptron with Inexact Search (2012) measured
The convergence guarantee of the structured perceptron assumes exact search for the best structure, yet practical systems such as incremental parsers and translation decoders use beam search.
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…
Statistical Syntax-Directed Translation with Extended Domain of Locality (2006)
The paper models syntax-directed translation as a tree-to-string transducer whose source side has multi-level trees, so each rule can cover a larger piece of the parse than a one-level rule.