Revisit Out-Of-Vocabulary Problem For Slot Filling: A Unified Contrastive Framework With Multi-Level Data Augmentations
Daichi Guo, Guanting Dong, Dayuan Fu, Yuxiang Wu, Chen Zeng, Tingfeng Hui, Liwen Wang, Xuefeng Li
Abstract
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.
BibTeX
@inproceedings{icassp2023_revisitoutofvoca,
title = {Revisit Out-Of-Vocabulary Problem For Slot Filling: A Unified Contrastive Framework With Multi-Level Data Augmentations},
author = {Daichi Guo and Guanting Dong and Dayuan Fu and Yuxiang Wu and Chen Zeng and Tingfeng Hui and Liwen Wang and Xuefeng Li and Zechen Wang and Keqing He and Xinyue Cui and Weiran Xu},
booktitle = {ICASSP 2023},
year = {2023}
}