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

Pre-trained models have achieved success in Chinese Short Text Matching (STM)tasks, but they often rely on superficial clues, leading to a lack of robustpredictions. To address this issue, it is crucial to analyze and mitigate theinfluence of superficial clues on STM models. Our study aims to investigatetheir over-reliance on the edit distance feature, commonly used to measure thesemantic similarity of Chinese text pairs, which can be considered asuperficial clue. To mitigate STM models' over-reliance on superficial clues,we propose a novel resampling training strategy called Gradually Learn SamplesContaining Superficial Clue (GLS-CSC). Through comprehensive evaluations ofIn-Domain (I.D.), Robustness (Rob.), and Out-Of-Domain (O.O.D.) test sets, wedemonstrate that GLS-CSC outperforms existing methods in terms of enhancing therobustness and generalization of Chinese STM models. Moreover, we conduct adetailed analysis of existing methods and reveal their commonality.

GLS-CSC: A Simple but Effective Strategy to Mitigate Chinese STM Models' Over-Reliance on Superficial Clue