English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we present a probabilistic framework for goal-driven spokendialog systems. A new dynamic stochastic state (DS-state) is then defined tocharacterize the goal set of a dialog state at different stages of the dialogprocess. Furthermore, an entropy minimization dialog management(EMDM) strategyis also proposed to combine with the DS-states to facilitate a robust andefficient solution in reaching a user's goals. A Song-On-Demand task, with atotal of 38117 songs and 12 attributes corresponding to each song, is used totest the performance of the proposed approach. In an ideal simulation, assumingno errors, the EMDM strategy is the most efficient goal-seeking method amongall tested approaches, returning the correct song within 3.3 dialog turns onaverage. Furthermore, in a practical scenario, with top five candidates tohandle the unavoidable automatic speech recognition (ASR) and natural languageunderstanding (NLU) errors, the results show that only 61.7\% of the dialoggoals can be successfully obtained in 6.23 dialog turns on average when randomquestions are asked by the system, whereas if the proposed DS-states areupdated with the top 5 candidates from the SLU output using the proposed EMDMstrategy executed at every DS-state, then a 86.7\% dialog success rate can beaccomplished effectively within 5.17 dialog turns on average. We alsodemonstrate that entropy-based DM strategies are more efficient thannon-entropy based DM. Moreover, using the goal set distributions in EMDM, theresults are better than those without them, such as in sate-of-the-art databasesummary DM.

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management through Dynamic Stochastic State Evolution