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

This paper investigates the application of machine learning (ML) techniquesto enable intelligent systems to learn multi-party turn-taking models fromdialogue logs. The specific ML task consists of determining who speaks next,after each utterance of a dialogue, given who has spoken and what was said inthe previous utterances. With this goal, this paper presents comparisons of theaccuracy of different ML techniques such as Maximum Likelihood Estimation(MLE), Support Vector Machines (SVM), and Convolutional Neural Networks (CNN)architectures, with and without utterance data. We present three corpora: thefirst with dialogues from an American TV situated comedy (chit-chat), thesecond with logs from a financial advice multi-bot system and the third with acorpus created from the Multi-Domain Wizard-of-Oz dataset (both aretopic-oriented). The results show: (i) the size of the corpus has a verypositive impact on the accuracy for the content-based deep learning approachesand those models perform best in the larger datasets; and (ii) if the dialoguedataset is small and topic-oriented (but with few topics), it is sufficient touse an agent-only MLE or SVM models, although slightly higher accuracies can beachieved with the use of the content of the utterances with a CNN model.

Learning Multi-Party Turn-Taking Models from Dialogue Logs