Poster   2017

Lison, Pierre; Kennington, Casey

Publikasjonsdetaljer

Lenker:

FULLTEKST: nr.no/~plison/pdfs/posters/semdial2017.pdf

We presented a simple approach to make neural dialogue models 'incremental' - that is, able to operate on incremental units instead of on complete utterances. The model can handle insertions, commit and revoke operations as well as incremental units associated with probabilities. A proof-of-concept experiment on a visual reference resolution task shows the promise of the approach.