David Chiang

4 paper cards in Mova's library · 2005–2010

David Chiang wrote 4 of the papers Mova reads, in 2005–2010, most of them on Machine translation, Treebanks; often with Mona Diab, Nizar Habash, Owen Rambow.

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

Papers

Learning to Translate with Source and Target Syntax (2010)
Tree-to-tree translation, with syntax on both sides, has often done worse than phrase-based systems. The paper studies why, and proposes a simpler method. Instead of forcing the two parse trees to match, it keeps the hierarchical phrase-based model (Hiero) and adds syntactic features to it: whether a span's source…
Hierarchical Phrase-Based Translation (2007)
This is the full version of the hierarchical model. Rules are extracted from a parallel text with no syntactic annotation, under length and nonterminal limits on the phrases they contain. The model is a synchronous context-free grammar with a log-linear score over features (phrase and lexical weights in both…
Parsing Arabic Dialects (2006)
Levantine Arabic (LA) is spoken, unwritten, and has almost no treebank, while MSA has the Penn Arabic Treebank (about 17,600 training sentences).
A Hierarchical Phrase-Based Model for Statistical Machine Translation (2005)
Chiang extends phrase-based translation with hierarchical phrases: phrase pairs that contain gaps filled by other phrase pairs.