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

Encoder-decoder based neural architectures serve as the basis ofstate-of-the-art approaches in end-to-end open domain dialog systems. Sincemost of such systems are trained with a maximum likelihood~(MLE) objective theysuffer from issues such as lack of generalizability and the generic responseproblem, i.e., a system response that can be an answer to a large number ofuser utterances, e.g., "Maybe, I don't know." Having explicit feedback on therelevance and interestingness of a system response at each turn can be a usefulsignal for mitigating such issues and improving system quality by selectingresponses from different approaches. Towards this goal, we present a systemthat evaluates chatbot responses at each dialog turn for coherence andengagement. Our system provides explicit turn-level dialog quality feedback,which we show to be highly correlated with human evaluation. To show thatincorporating this feedback in the neural response generation models improvesdialog quality, we present two different and complementary mechanisms toincorporate explicit feedback into a neural response generation model:reranking and direct modification of the loss function during training. Ourstudies show that a response generation model that incorporates these combinedfeedback mechanisms produce more engaging and coherent responses in anopen-domain spoken dialog setting, significantly improving the response qualityusing both automatic and human evaluation.

Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators