Online Supervised Learning of Non-Understanding Recovery Policies

Bohus, Dan; Langner, Brian; Raux, Antoine; Black, Alan W.; Eskénazi, Maxine; Rudnicky, Alex

doi:10.1109/slt.2006.326844

Cited by 17 publications

(8 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These features help in capturing the task-specific characteristics of the events when social behavior should be performed. The 37 steps in the tutor's interaction plan are represented as binary features [Bohus et al 2006] indicating which step of the interaction is being executed. We included the information about the dialog state before and after the event using this feature representation.…”

Section: Featuresmentioning

confidence: 99%

“…The most popular current application of such agents is information access typically using voice-based IO over telephones and mobile devices. At the core of these agents are models that represent the structure of the interaction [Rudnicky and Xu 1999;Freedman 2000;Bangalore et al 2006] and perform functions such as belief update [Williams 2007], confidence annotation [Bohus and Rudnicky 2007], timing [Raux and Eskenazi 2009], and action selection [Paek and Horvitz 2000;Bohus et al 2006;Williams and Young 2007].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Triggering effective social support for online groups

Kumar

Rosé

2014

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

Conversational agent technology is an emerging paradigm for creating a social environment in online groups that is conducive to effective teamwork. Prior work has demonstrated advantages in terms of learning gains and satisfaction scores when groups learning together online have been supported by conversational agents that employ Balesian social strategies. This prior work raises two important questions that are addressed in this article. The first question is one of generality. Specifically, are the positive effects of the designed support specific to learning contexts? Or are they in evidence in other collaborative task domains as well? We present a study conducted within a collaborative decision-making task where we see that the positive effects of the Balesian social strategies extend to this new context. The second question is whether it is possible to increase the effectiveness of the Balesian social strategies by increasing the context sensitivity with which the social strategies are triggered. To this end, we present technical work that increases the sensitivity of the triggering. Next, we present a user study that demonstrates an improvement in performance of the support agent with the new, more sensitive triggering policy over the baseline approach from prior work.The technical contribution of this article is that we extend prior work where such support agents were modeled using a composition of conversational behaviors integrated within an event-driven framework. Within the present approach, conversation is orchestrated through context-sensitive triggering of the composed behaviors. The core effort involved in applying this approach involves building a set of triggering policies that achieve this orchestration in a time-sensitive and coherent manner. In line with recent developments in data-driven approaches for building dialog systems, we present a novel technique for learning behaviorspecific triggering policies, deploying it as part of our efforts to improve a socially capable conversational tutor agent that supports collaborative learning.

show abstract

Section: Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Triggering effective social support for online groups

Kumar

Rosé

2014

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…While some authors have made progress towards learning dialogue behaviour from human-machine interaction, they still rely on some form of simulation or delayed re-training. [11], for example, describe a spoken dialogue system that learns to optimize its non-understanding recovery strategies on-line through interactions with human users based on pre-trained logistic regression models. The system is re-trained every day.…”

Section: From Virtual Assistants To Interactive Conversational Robotsmentioning

confidence: 99%

Machine learning for interactive systems and robots

Cuayáhuitl

Otterlo

Dethlefs

et al. 2013

Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Co

View full text Add to dashboard Cite

Research on interactive systems and robots, i.e. interactive machines that perceive, act and communicate, has applied a multitude of different machine learning frameworks in recent years, many of which are based on a form of reinforcement learning (RL). In this paper, we will provide a brief introduction to the application of machine learning techniques in interactive learning systems. We identify several dimensions along which interactive learning systems can be analyzed. We argue that while many applications of interactive machines seem different at first sight, sufficient commonalities exist in terms of the challenges faced. By identifying these commonalities between (learning) approaches, and by taking interdisciplinary approaches towards the challenges, we anticipate more effective design and development of sophisticated machines that perceive, act and communicate in complex, dynamic and uncertain environments.

show abstract

“…Early work that addressed confidence annotation of input to the dialogue manager illustrated how low-level ASR features interact with features from natural language understanding and dialogue management. Confidence annotation has been done through linear regression models whose predictors include parse and dialogue state, relying on at most a dozen features to learn a binary threshold [41], [42]. When learning was done over multiple days for nine recovery strategies, system performance improved [42].…”

Section: Related Workmentioning

confidence: 99%

“…Confidence annotation has been done through linear regression models whose predictors include parse and dialogue state, relying on at most a dozen features to learn a binary threshold [41], [42]. When learning was done over multiple days for nine recovery strategies, system performance improved [42]. Confidence scores can also be continuous.…”

Section: Related Workmentioning

confidence: 99%

Naturalistic Dialogue Management for Noisy Speech Recognition

Passonneau

Epstein

Ligorio

2012

IEEE J. Sel. Top. Signal Process.

View full text Add to dashboard Cite

With naturalistic dialogue management, a spoken dialogue system behaves as a human would under similar conditions. This paper reports on an experiment to develop naturalistic clarification strategies for noisy speech recognition in the context of spoken dialogue systems. We collected a wizard-of-Oz corpus in which human wizards with access to a rich set of clarification actions made clarification decisions online, based on human-readable versions of system data. The experiment compares an evaluation of calls to a baseline system in a library domain with calls to an enhanced version of the system. The new system has a clarification module based on the wizard data that is a decision tree constructed from three machine-learned models. It replicates the wizards' ability to ground partial understandings of noisy input and to build upon them. The enhanced system has a significantly higher rate of task completion, greater task success and improved efficiency.

show abstract

Online Supervised Learning of Non-Understanding Recovery Policies

Cited by 17 publications

References 6 publications

Triggering effective social support for online groups

Triggering effective social support for online groups

Machine learning for interactive systems and robots

Naturalistic Dialogue Management for Noisy Speech Recognition

Contact Info

Product

Resources

About