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

Short text clustering is challenging since it takes imbalanced and noisy dataas inputs. Existing approaches cannot solve this problem well, since (1) theyare prone to obtain degenerate solutions especially on heavy imbalanceddatasets, and (2) they are vulnerable to noises. To tackle the above issues, wepropose a Robust Short Text Clustering (RSTC) model to improve robustnessagainst imbalanced and noisy data. RSTC includes two modules, i.e.,pseudo-label generation module and robust representation learning module. Theformer generates pseudo-labels to provide supervision for the later, whichcontributes to more robust representations and correctly separated clusters. Toprovide robustness against the imbalance in data, we propose self-adaptiveoptimal transport in the pseudo-label generation module. To improve robustnessagainst the noise in data, we further introduce both class-wise andinstance-wise contrastive learning in the robust representation learningmodule. Our empirical studies on eight short text clustering datasetsdemonstrate that RSTC significantly outperforms the state-of-the-art models.The code is available at: https://github.com/hmllmh/RSTC.

Robust Representation Learning with Reliable Pseudo-labels Generation via Self-Adaptive Optimal Transport for Short Text Clustering