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

Most dialogue systems in real world rely on predefined intents and answersfor QA service, so discovering potential intents from large corpus previouslyis really important for building such dialogue services. Considering that mostscenarios have few intents known already and most intents waiting to bediscovered, we focus on semi-supervised text clustering and try to make theproposed method benefit from labeled samples for better overall clusteringperformance. In this paper, we propose Deep Contrastive Semi-supervisedClustering (DCSC), which aims to cluster text samples in a semi-supervised wayand provide grouped intents to operation staff. To make DCSC fully utilize thelimited known intents, we propose a two-stage training procedure for DCSC, inwhich DCSC will be trained on both labeled samples and unlabeled samples, andachieve better text representation and clustering performance. We conductexperiments on two public datasets to compare our model with several popularmethods, and the results show DCSC achieve best performance across all datasetsand circumstances, indicating the effect of the improvements in our work.

Semi-Supervised Clustering with Contrastive Learning for Discovering New Intents