Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...
We present a novel approach to word reordering which successfully integrates syntactic structural knowledge with phrase-based SMT. This is done by constructing a lattice of altern...
The alignment problem--establishing links between corresponding phrases in two related sentences--is as important in natural language inference (NLI) as it is in machine translati...
Bill MacCartney, Michel Galley, Christopher D. Man...