Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations
This addresses a domain-specific problem in natural language processing for dialogue systems, offering an incremental improvement by enhancing robustness to OOV issues.
The paper tackles the Out-of-Vocabulary (OOV) problem in slot filling for dialogue systems, where existing models struggle with generalization due to memorizing entity patterns, and proposes a unified contrastive framework with multi-level data augmentations, achieving state-of-the-art performance on two datasets for both OOV slots and words.
In real dialogue scenarios, the existing slot filling model, which tends to memorize entity patterns, has a significantly reduced generalization facing Out-of-Vocabulary (OOV) problems. To address this issue, we propose an OOV robust slot filling model based on multi-level data augmentations to solve the OOV problem from both word and slot perspectives. We present a unified contrastive learning framework, which pull representations of the origin sample and augmentation samples together, to make the model resistant to OOV problems. We evaluate the performance of the model from some specific slots and carefully design test data with OOV word perturbation to further demonstrate the effectiveness of OOV words. Experiments on two datasets show that our approach outperforms the previous sota methods in terms of both OOV slots and words.