Incremental Semantics for Dialogue Processing: Requirements, and a Comparison of Two Approaches - Université Paris Cité Access content directly
Conference Papers Year :

Incremental Semantics for Dialogue Processing: Requirements, and a Comparison of Two Approaches

Abstract

Truly interactive dialogue systems need to construct meaning on at least a word-byword basis. We propose desiderata for incremental semantics for dialogue models and systems, a task not heretofore attempted thoroughly. After laying out the desirable properties we illustrate how they are met by current approaches, comparing two incremental semantic processing frameworks: Dynamic Syntax enriched with Type Theory with Records (DS-TTR) and Robust Minimal Recursion Semantics with incremental processing (RMRS-IP). We conclude these approaches are not significantly different with regards to their semantic representation construction, however their purported role within semantic models and dialogue models is where they diverge.

Domains

Linguistics
Fichier principal
Vignette du fichier
HoughEtAl15IWCS.pdf (1.07 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Loading...

Dates and versions

hal-01371420 , version 1 (26-09-2016)

Identifiers

  • HAL Id : hal-01371420 , version 1

Cite

Julian Hough, Casey Kennington, David Schlangen, Jonathan Ginzburg. Incremental Semantics for Dialogue Processing: Requirements, and a Comparison of Two Approaches. 11th International Conference on Computational Semantics, 2015, London, United Kingdom. ⟨hal-01371420⟩
198 View
393 Download

Share

Gmail Facebook Twitter LinkedIn More