Individual and Domain Adaptation in Sentence Planning for Dialogue

TL;DR

This paper presents a trainable sentence planning approach for dialogue systems that adapts to individual users and domains, producing high-quality, personalized responses comparable to template-based methods.

Contribution

It introduces a trainable sentence planner capable of adapting to individual preferences and domain features, demonstrating improved personalization and flexibility over traditional template-based systems.

Findings

Trainable sentence planning achieves quality comparable to template-based generators.

Individualized models outperform population-based models in sentence planning.

N-gram features are often as effective as higher-level linguistic features.

Abstract

One of the biggest challenges in the development and deployment of spoken dialogue systems is the design of the spoken language generation module. This challenge arises from the need for the generator to adapt to many features of the dialogue domain, user population, and dialogue context. A promising approach is trainable generation, which uses general-purpose linguistic knowledge that is automatically adapted to the features of interest, such as the application domain, individual user, or user group. In this paper we present and evaluate a trainable sentence planner for providing restaurant information in the MATCH dialogue system. We show that trainable sentence planning can produce complex information presentations whose quality is comparable to the output of a template-based generator tuned to this domain. We also show that our method easily supports adapting the sentence planner to individuals, and that the individualized sentence planners generally perform better than models trained and tested on a population of individuals. Previous work has documented and utilized individual preferences for content selection, but to our knowledge, these results provide the first demonstration of individual preferences for sentence planning operations, affecting the content order, discourse structure and sentence structure of system responses. Finally, we evaluate the contribution of different feature sets, and show that, in our application, n-gram features often do as well as features based on higher-level linguistic representations.