Individual and Domain Adaptation in Sentence Planning for Dialogue

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.

References in corpus (4)

• Inferring Strategies for Sentence Ordering in Multidocument News Summarization
• Learning Content Selection Rules for Generating Object Descriptions in Dialogue
• Acquiring Correct Knowledge for Natural Language Generation
• Bootstrapping Lexical Choice via Multiple-Sequence Alignment

Cited by in corpus (15)

• Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
• Developing Enhanced Conversational Agents for Social Virtual Worlds
• RankME: Reliable Human Ratings for Natural Language Generation
• Multi-domain Neural Network Language Generation for Spoken Dialogue Systems
• Adversarial Domain Adaptation for Variational Neural Language Generation in Dialogue Systems
• Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
• Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation
• A System for Automatic English Text Expansion
• Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue
• Content Selection in Data-to-Text Systems: A Survey
• Athena: Constructing Dialogues Dynamically with Discourse Constraints
• Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
• Towards End-to-End Learning for Efficient Dialogue Agent by Modeling Looking-ahead Ability
• Tree-Structured Semantic Encoder with Knowledge Sharing for Domain Adaptation in Natural Language Generation
• Natural Language Generation as Planning under Uncertainty Using Reinforcement Learning