Decay-Function-Free Time-Aware Attention to Context and Speaker Indicator for Spoken Language Understanding
This work addresses improving accuracy in spoken language understanding for dialogue systems, representing an incremental advancement with specific gains in a domain-specific context.
The authors tackled the problem of capturing salient contextual information in spoken language understanding by proposing time-aware models that learn latent time-decay functions automatically and a method to label the current speaker, achieving significantly higher F1 scores than state-of-the-art contextual models on the Dialog State Tracking Challenge 4 benchmark dataset.
To capture salient contextual information for spoken language understanding (SLU) of a dialogue, we propose time-aware models that automatically learn the latent time-decay function of the history without a manual time-decay function. We also propose a method to identify and label the current speaker to improve the SLU accuracy. In experiments on the benchmark dataset used in Dialog State Tracking Challenge 4, the proposed models achieved significantly higher F1 scores than the state-of-the-art contextual models. Finally, we analyze the effectiveness of the introduced models in detail. The analysis demonstrates that the proposed methods were effective to improve SLU accuracy individually.