SNOiC: Soft Labeling and Noisy Mixup based Open Intent Classification Model
This addresses the problem of identifying unknown intents in dialogue systems, which is incremental as it builds on existing methods to improve robustness and data scarcity issues.
The paper tackles open intent classification by proposing SNOiC, which uses soft labeling and noisy mixup to reduce bias and generate pseudo-data for open intents, achieving performance improvements of 0.93% to 12.76% over state-of-the-art models on benchmark datasets.
This paper presents a Soft Labeling and Noisy Mixup-based open intent classification model (SNOiC). Most of the previous works have used threshold-based methods to identify open intents, which are prone to overfitting and may produce biased predictions. Additionally, the need for more available data for an open intent class presents another limitation for these existing models. SNOiC combines Soft Labeling and Noisy Mixup strategies to reduce the biasing and generate pseudo-data for open intent class. The experimental results on four benchmark datasets show that the SNOiC model achieves a minimum and maximum performance of 68.72\% and 94.71\%, respectively, in identifying open intents. Moreover, compared to state-of-the-art models, the SNOiC model improves the performance of identifying open intents by 0.93\% (minimum) and 12.76\% (maximum). The model's efficacy is further established by analyzing various parameters used in the proposed model. An ablation study is also conducted, which involves creating three model variants to validate the effectiveness of the SNOiC model.