Kevin Knight · page 2

30 papers in our library · 1991–2017 · page 2 of 2

Papers

The most cited first (OpenAlex and our library).

SPMT: Statistical Machine Translation with Syntactified Target Language Phrases (2006 · 96 citations)
Phrase-based statistical MT handles lexical choice well but often produces ungrammatical word order for syntactically divergent pairs such as Chinese–English.
Binarization of Synchronous Context-Free Grammars (2009 · 84 citations)
Syntax-based machine translation built on synchronous context-free grammars (SCFGs) or tree transducers, such as rules extracted following Galley et al.
Training Tree Transducers (2004 · 53 citations)
The paper argues that probabilistic models of language should be written as tree transducers, since the theory of tree automata is well developed and gives tools that string models have.
Capturing Language-Specific Semantic Distinctions in Interlingua-based MT (1991 · 21 citations)
The paper describes an English-Spanish system (KBNL) that uses a Discourse Representation Structure (DRS) as its interlingua.
Mapping Between English Strings and Reentrant Semantic Graphs (2014 · 14 citations)
The paper asks whether graph transduction formalisms with good computational properties can concisely describe how English expresses reentrancy in semantic graphs, where one entity fills several roles.