Generation and evaluation of user tailored responses in multimodal dialogue

By Marilyn A. Walker, S. Whittaker, Amanda Stent, Preetam Maloor, Johanna D. Moore, Michael Johnston, Gunaranjan Vasireddy. 2004

129 citations recorded by the source corpus.

When people engage in conversation, they tailor their utterances to their conversational partners, whether these partners are other humans or computational systems. This tailoring, or adaptation to the partner takes place in all facets of human language use, and is based on a mental model or a user model of the conversational partner. Such adaptation has been shown to improve listeners' comprehension, their satisfaction with an interactive system, the efficiency with which they execute conversational tasks, and the likelihood of achieving higher level goals such as changing the listener's beliefs and attitudes. We focus on one aspect of adaptation, namely the tailoring of the content of dialogue system utterances for the higher level processes of persuasion, argumentation and advice-giving. Our hypothesis is that algorithms that adapt content for these processes, according to a user model, will improve the usability, efficiency, and effectiveness of dialogue systems. We describe a multimodal dialogue system and algorithms for adaptive content selection based on multi-attribute decision theory. We demonstrate experimentally the improved efficacy of system responses through the use of user models to both tailor the content of system utterances and to manipulate their conciseness.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

The E2E Dataset: New Challenges For End-to-End Generation (2017, methodology): “family restaurant”. The majority of our data, however, contains more complex, varied syntactic structures, including phenomena explicitly modelled by early statistical approaches (Stent et al., 2004; Walker et al., 2004). For exFigure 3: D-Level sentence distribution of the datasets under comparison”
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, background): “The majority of our data, however, contains more complex, varied syntactic structures, including phenomena explicitly modelled by early statistical approaches to NLG (Stent, Prasad, and Walker 2004; Walker et al. 2004).”
Natural Language Generation as Planning Under Uncertainty for Spoken Dialogue Systems (2009, methodology): “This is a task common to much prior work in NLG, e.g. (Walker et al., 2004; Demberg and Moore, 2006; Polifroni and Walker, 2008).”
Individual and Domain Adaptation in Sentence Planning for Dialogue (2007, methodology): “Paiva and Evans (2004) present a technique for training a generator by learning the relationship between particular generation decisions and text variables that can be measured in the output corpus.”
The Personalization of Conversational Agents in Health Care: Systematic Review (2019, background): “The effects of personalization have been evaluated in various ways by measuring aspects like efficiency in terms of the number and duration of interactions [11,20], user satisfaction, relevance, and understandability [20], information quality presented [21], and appropriateness of system responses [”
A Survey on Conversational Recommender Systems (2020, background): “The dialogue system presented in [142], for example, supports multiple types of inputs, including visual inputs on a geographic map, pen gestures like zooming, or handwritten input.”
Explainable Autonomy: A Study of Explanation Styles for Building Clear Mental Models (2018, background): “Previous studies in NLG have included adapting to style (Dethlefs et al., 2014), preferences (Walker et al., 2004), knowledge (Janarthanam and Lemon, 2014) and the context (Dethlefs, 2014) of the user.”