Spoken Dialogue Systems

Jokinen, Kristiina; McTear, Michael F.

doi:10.2200/s00204ed1v01y200910hlt005

Cited by 70 publications

(53 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We use Pyro's finite state machines paradigm to implement state transitions for dialogue control, a well-known approach in spoken dialogue systems [4]. Other uses of finite state machines in robotics are described in [1].…”

Section: Spoken Dialoguesmentioning

confidence: 99%

Adding Speech to a Robotics Simulator

Wilcock

Jokinen

2011

Proceedings of the Paralinguistic Information and Its Integration in Spoken Dialogue Systems Workshop

Self Cite

View full text Add to dashboard Cite

We present a demo showing different levels of emergent verbal behaviour that arise when speech is added to a robotics simulator. After showing examples of (silent) robot activities in the simulator, adding speech output enables the robot to give spoken explanations of its behaviour. Adding speech input allows the robot's movements to be guided by voice commands. In addition, the robot can modify its own verbal behaviour when asked to talk less or more. The robotics toolkit supports different behavioural paradigms, including finite state machines. The demo shows an example state transition based spoken dialogue system implemented within the robotics framework. Other more experimental combinations of speech and robot behaviours will also be shown.

show abstract

Section: Spoken Dialoguesmentioning

confidence: 99%

Adding Speech to a Robotics Simulator

Wilcock

Jokinen

2011

Proceedings of the Paralinguistic Information and Its Integration in Spoken Dialogue Systems Workshop

Self Cite

View full text Add to dashboard Cite

show abstract

“…The mainstream architecture for virtual agents in dialogue systems (McTear, 2004;Jokinen and McTear, 2009;Rieser and Lemon, 2011;Young et al, 2013) involves a combination of several components, which require a lot of expertise in the different technologies, considerable development and implementation effort to adapt each component to a new domain, and are only partially trainable (if at all). Recently, Vinyals and Le (2015), Serban et al (2015), proposed to replace this complex architecture by a single network (such as a Long Short Term Memory (LSTM) (Hochreiter and Schmidhuber, 1997)) that predicts the agent's response from the dialogue history up to the point where it should be produced: this network can be seen as a form of conditional neural language model (LM), where the dialogue history provides the context for the production of the next agent's utterance.…”

Section: Introductionmentioning

confidence: 99%

LSTM-Based Mixture-of-Experts for Knowledge-Aware Dialogues

Dymetman

Renders

2016

Proceedings of the 1st Workshop on Representation Learning for NLP

View full text Add to dashboard Cite

We introduce an LSTM-based method for dynamically integrating several wordprediction experts to obtain a conditional language model which can be good simultaneously at several subtasks. We illustrate this general approach with an application to dialogue where we integrate a neural chat model, good at conversational aspects, with a neural question-answering model, good at retrieving precise information from a knowledge-base, and show how the integration combines the strengths of the independent components. We hope that this focused contribution will attract attention on the benefits of using such mixtures of experts in NLP and dialogue systems specifically.

show abstract

“…to book flights, to receive information about bus or train timetables, to detect computer faults, etc. (Jokinen & McTear, 2009). Usually, such tasks do not include argumentation.…”

Section: Introductionmentioning

confidence: 99%

A computational model of argumentation in agreement negotiation processes

Koit¹,

Õim²

2014

Argument & Computation

View full text Add to dashboard Cite

The paper describes a computational model that we have implemented in an experimental dialogue system (DS). Communication in a natural language between two participants A and B is considered, where A has a communicative goal that his/her partner B will make a decision to perform an action D. A argues the usefulness, pleasantness, etc. of D (including its consequences), in order to guide B's reasoning in a desirable direction. A computational model of argumentation is developed, which includes reasoning. Our model is based on the studies in the common-sense conception of how the human mind works in such situations. Theoretical considerations are followed by an analysis of Estonian spoken human-human dialogues. First, calls of clients to travel agencies are studied where a travel agent could use various arguments in order to persuade a client to book a trip. The analysis demonstrates that clients are primarily looking for information; argumentation occurs in a small number of dialogues. Secondly, calls of sales clerks of an educational company to different organisations are analysed where training courses are offered. The sales clerks, unlike the travel agents, try to persuade clients, stressing the usefulness of a course. Finally, face-to-face conversations are studied where one participant is arguing for an action by the partner. The corpus analysis shows that our model covers simple situations occurred in actual dialogues. Therefore, we have chosen a limited application of the model in a DS -communication trainer. The computer can optionally perform A's or B's role and the interaction with the user in Estonian follows norms and rules of human-human communication.

show abstract

Spoken Dialogue Systems

Cited by 70 publications

References 105 publications

Adding Speech to a Robotics Simulator

Adding Speech to a Robotics Simulator

LSTM-Based Mixture-of-Experts for Knowledge-Aware Dialogues

A computational model of argumentation in agreement negotiation processes

Contact Info

Product

Resources

About