Towards an Ontology-Driven Adaptive Dialogue Framework

Abstract

In this paper, we describe the principles and technologies that underpin the development of an adaptive dialogue manager framework, tailored to carrying out human-agent conversations in a natural, robust and flexible manner. Our research focus is twofold. First, the investigation of dialogue strategies that can handle dynamically created user and system actions, while still enabling the agent to adapt its actions to various and possibly changing contexts. Second, the utilisation of rich semantic annotations for capturing background knowledge, as well as conversation topics and semantics of user utterances extracted through language analysis. The resulting annotations comprise the situational descriptions upon which reasoning takes place to recognise the conversation context and compile appropriate responses.

Enabling Dialogue Management with Dynamically Created Dialogue Actions

“…As described by Meditskos et al [5], modules for advanced techniques in the fields of language analysis as well as knowledge interpretation and reasoning need to be integrated in order to support dynamically created dialogue actions both by the user and the system. To facilitate the interaction with such modules, the Model and the View of OwlSpeak need to be adapted.…”

“…In this work, we describe the implementation and evaluation of the extension of the already existing OwlSpeak DM [3,13] in order to handle dynamically created user and system actions, utilising general dialogue actions combined with ontol-ogy semantics to determine the system behaviour based on [5,11]. The structure of the paper is as follows: In Section 2, the original OwlSpeak DM is introduced.…”

Automatic Modification of Communication Style in Dialogue Management

“…Our approaches to the automatic generation of CS are developed as part of the KRISTINA Project Meditskos et al, 2016). At the core of the aspired system, a DM component decides on the next system action.…”

Towards Reasoned Modality Selection in an Embodied Conversation Agent

“…For this purpose, it solicits first from the KI module possible reactions that are reasoned over the KB. In other words, in contrast to most of the state-of-the-art DM models, the determination of the turn of the system is distributed between a high level control DM and a reasoning KB module; see [15] for details. On its way to the MS module, the DM output is enriched by communicative labels.…”