Applying POMDPs to Dialog Systems in the Troubleshooting Domain
نویسنده
چکیده
This paper reports on progress applying partially observable Markov decision processes (POMDPs) to a commercial dialog domain: troubleshooting. In the troubleshooting domain, a spoken dialog system helps a user to fix a product such as a failed DSL connection. Past work has argued that a POMDP is a principled approach to building spoken dialog systems in the simpler slot-filling domain; this paper explains how the POMDPs formulation can be extended to the more complex troubleshooting domain. Results from dialog simulation verify that a POMDP outperforms a handcrafted baseline.
منابع مشابه
NAACL - HLT 2007 Bridging the Gap : Academic and Industrial Research in Dialog Technologies
This paper reports on progress applying partially observable Markov decision processes (POMDPs) to a commercial dialog domain: troubleshooting. In the troubleshooting domain, a spoken dialog system helps a user to fix a product such as a failed DSL connection. Past work has argued that a POMDP is a principled approach to building spoken dialog systems in the simpler slot-filling domain; this pa...
متن کاملA case study of applying decision theory in the real world: POMDPs and spoken dialog systems
Spoken dialog systems present a classic example of planning under uncertainty. Speech recognition errors are ubiquitous and impossible to detect reliably, so the state of the conversation can never be known with certainty. Despite this, the system must choose actions to make progress to a long term goal. As such, decision theory, and in particular partiallyobservable Markov decision processes (...
متن کاملThe best of both worlds: unifying conventional dialog systems and POMDPs
Partially observable Markov decision processes (POMDPs) and conventional design practices offer two very different but complementary approaches to building spoken dialog systems. Whereas conventional manual design readily incorporates business rules, domain knowledge, and contextually appropriate system language, POMDPs employ optimization to produce more detailed dialog plans and better robust...
متن کاملScaling POMDPs for dialog management with composite summary point-based value iteration (CSPBVI)
Although partially observable Markov decision processes (POMDPs) have shown great promise as a framework for dialog management in spoken dialog systems, important scalability issues remain. This paper tackles the problem of scaling slot-filling POMDP-based dialog managers to many slots with a novel technique called composite point-based value iteration (CSPBVI). CSPBVI creates a “local” POMDP p...
متن کاملHelp Yourself : A Virtual Self-Assist Agent
In this work, we describe an unsupervised framework for creating self-assist systems which can serve as virtual call center agents to guide the customer in performing different domain-dependent tasks (like troubleshooting a problem, changing settings etc.). We describe a framework for creating an intent graph from a corpus of knowledge articles from a given domain which is used in creating the ...
متن کامل