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

Selecting an appropriate response from many candidates given the utterancesin a multi-turn dialogue is the key problem for a retrieval-based dialoguesystem. Existing work formalizes the task as matching between the utterancesand a candidate and uses the cross-entropy loss in learning of the model. Thispaper applies contrastive learning to the problem by using the supervisedcontrastive loss. In this way, the learned representations of positive examplesand representations of negative examples can be more distantly separated in theembedding space, and the performance of matching can be enhanced. We furtherdevelop a new method for supervised contrastive learning, referred to astwo-level supervised contrastive learning, and employ the method in responseselection in multi-turn dialogue. Our method exploits two techniques: sentencetoken shuffling (STS) and sentence re-ordering (SR) for supervised contrastivelearning. Experimental results on three benchmark datasets demonstrate that theproposed method significantly outperforms the contrastive learning baseline andthe state-of-the-art methods for the task.

Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue