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

Modeling human conversations is the essence for building satisfying chat-botswith multi-turn dialog ability. Conversation modeling will notably benefit fromdomain knowledge since the relationships between sentences can be clarified dueto semantic hints introduced by knowledge. In this paper, a deep neural networkis proposed to incorporate background knowledge for conversation modeling.Through a specially designed Recall gate, domain knowledge can be transformedinto the extra global memory of Long Short-Term Memory (LSTM), so as to enhanceLSTM by cooperating with its local memory to capture the implicit semanticrelevance between sentences within conversations. In addition, this paperintroduces the loose structured domain knowledge base, which can be built withslight amount of manual work and easily adopted by the Recall gate. Our modelis evaluated on the context-oriented response selecting task, and experimentalresults on both two datasets have shown that our approach is promising formodeling human conversations and building key components of automatic chattingsystems.

Incorporating Loose-Structured Knowledge into Conversation Modeling via Recall-Gate LSTM