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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Dialog response selection is an important step towards natural responsegeneration in conversational agents. Existing work on neural conversationalmodels mainly focuses on offline supervised learning using a large set ofcontext-response pairs. In this paper, we focus on online learning of responseselection in retrieval-based dialog systems. We propose a contextualmulti-armed bandit model with a nonlinear reward function that uses distributedrepresentation of text for online response selection. A bidirectional LSTM isused to produce the distributed representations of dialog context andresponses, which serve as the input to a contextual bandit. In learning thebandit, we propose a customized Thompson sampling method that is applied to apolynomial feature space in approximating the reward. Experimental results onthe Ubuntu Dialogue Corpus demonstrate significant performance gains of theproposed method over conventional linear contextual bandits. Moreover, wereport encouraging response selection performance of the proposed neural banditmodel using the Recall@k metric for a small set of online training samples.

Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models