Mova0.5 pre-release⌕
☰
home / docs / papers / authors / Jason Eisner

Jason Eisner

3 paper cards in Mova's library · 2003–2016

Jason Eisner wrote 3 of the papers Mova reads, in 2003–2016, most of them on Machine translation, Treebanks; often with David Smith, Dingquan Wang.

OpenAlex · ORCID · h-index 51 · 8141 citations · 307 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 2 · Treebanks 1

Papers

  1. The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages (2016)
    Galactic Dependencies 1.0 is a set of synthetic languages in UD format. Each is made from a real UD treebank by permuting the order of the dependents of nouns and verbs, to match the word order of other real languages. Starting from 37 real treebanks, the set gives 53,428 languages in total. The authors check realism…
  2. Quasi-Synchronous Grammars: Alignment by Soft Projection of Syntactic Dependencies (2006)
    The paper defines quasi-synchronous grammar (QG). Given the parse tree of the source sentence, a QG builds a monolingual grammar over target trees. The target tree need not be isomorphic to the source. Each target node is aligned to at most one source node, and the allowed relations between a target parent-child pair…
  3. Learning Non-Isomorphic Tree Mappings for Machine Translation (2003)
    Eisner proposes learning a mapping between two trees that need not have the same shape. The model is a synchronous tree substitution grammar (STSG): a set of pairs of elementary trees, each pair with a state for every open position, which combine into a pair of derived trees. He gives a probabilistic form, a tree…

Co-authors (2)

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