DSTEA: Improving Dialogue State Tracking via Entity Adaptive Pre-training
This work addresses a bottleneck in dialogue systems by offering a pre-training approach that boosts DST models without requiring external knowledge integration, though it is incremental as it builds on existing pre-training methods.
The paper tackled the problem of improving Dialogue State Tracking (DST) performance by proposing DSTEA, an entity adaptive pre-training method that enhances encoders through intensive training on key entities, resulting in up to a 2.69% increase in joint goal accuracy on MultiWOZ datasets.
Dialogue State Tracking (DST) is critical for comprehensively interpreting user and system utterances, thereby forming the cornerstone of efficient dialogue systems. Despite past research efforts focused on enhancing DST performance through alterations to the model structure or integrating additional features like graph relations, they often require additional pre-training with external dialogue corpora. In this study, we propose DSTEA, improving Dialogue State Tracking via Entity Adaptive pre-training, which can enhance the encoder through by intensively training key entities in dialogue utterances. DSTEA identifies these pivotal entities from input dialogues utilizing four different methods: ontology information, named-entity recognition, the spaCy, and the flair library. Subsequently, it employs selective knowledge masking to train the model effectively. Remarkably, DSTEA only requires pre-training without the direct infusion of extra knowledge into the DST model. This approach resulted in substantial performance improvements of four robust DST models on MultiWOZ 2.0, 2.1, and 2.2, with joint goal accuracy witnessing an increase of up to 2.69% (from 52.41% to 55.10%). Further validation of DSTEA's efficacy was provided through comparative experiments considering various entity types and different entity adaptive pre-training configurations such as masking strategy and masking rate.