MetaASSIST: Robust Dialogue State Tracking with Meta Learning
This work addresses noise in dialogue state annotations for DST models, offering an incremental improvement over the ASSIST framework by making weighting parameters adaptive.
The paper tackles the problem of noisy state annotations in dialogue datasets, which degrade dialogue state tracking (DST) model performance, by proposing MetaASSIST, a meta learning-based framework that adaptively learns weighting parameters for pseudo labels, achieving a state-of-the-art joint goal accuracy of 80.10% on MultiWOZ 2.4.
Existing dialogue datasets contain lots of noise in their state annotations. Such noise can hurt model training and ultimately lead to poor generalization performance. A general framework named ASSIST has recently been proposed to train robust dialogue state tracking (DST) models. It introduces an auxiliary model to generate pseudo labels for the noisy training set. These pseudo labels are combined with vanilla labels by a common fixed weighting parameter to train the primary DST model. Notwithstanding the improvements of ASSIST on DST, tuning the weighting parameter is challenging. Moreover, a single parameter shared by all slots and all instances may be suboptimal. To overcome these limitations, we propose a meta learning-based framework MetaASSIST to adaptively learn the weighting parameter. Specifically, we propose three schemes with varying degrees of flexibility, ranging from slot-wise to both slot-wise and instance-wise, to convert the weighting parameter into learnable functions. These functions are trained in a meta-learning manner by taking the validation set as meta data. Experimental results demonstrate that all three schemes can achieve competitive performance. Most impressively, we achieve a state-of-the-art joint goal accuracy of 80.10% on MultiWOZ 2.4.