This paper describes recent efforts at Linguistic Data Consortium at the University of Pennsylvania to create manual transcripts as a shared resource for human language technology...
We present a linguistically-motivated algorithm for reconstructing nonlocal dependency in broad-coverage context-free parse trees derived from treebanks. We use an algorithm based...
We compare two pivot strategies for phrase-based statistical machine translation (SMT), namely phrase translation and sentence translation. The phrase translation strategy means t...
A natural language generation system must generate expressions that allow a reader to identify the entities to which they refer. This paper describes the creation of referring-exp...
Jill Nickerson, Stuart M. Shieber, Barbara J. Gros...
This paper describes the Arabic broadcast transcription system fielded by IBM in the GALE Phase 3.5 machine translation evaluation. Key advances compared to our Phase 2.5 system ...
George Saon, Hagen Soltau, Upendra Chaudhari, Step...