Large-Scale Multi-Domain Belief Tracking with Knowledge Sharing

TL;DR

This paper introduces a scalable multi-domain belief tracking model that leverages semantic similarity for knowledge sharing, significantly improving performance on large, complex dialogue datasets.

Contribution

The paper presents a novel approach that utilizes semantic similarity to enable knowledge sharing across domains, addressing scalability issues in dialogue belief tracking.

Findings

Outperforms existing models in multi-domain belief tracking

Demonstrates robustness on a large, diverse dialogue dataset

Shows improved accuracy over state-of-the-art single-domain models

Abstract

Robust dialogue belief tracking is a key component in maintaining good quality dialogue systems. The tasks that dialogue systems are trying to solve are becoming increasingly complex, requiring scalability to multi domain, semantically rich dialogues. However, most current approaches have difficulty scaling up with domains because of the dependency of the model parameters on the dialogue ontology. In this paper, a novel approach is introduced that fully utilizes semantic similarity between dialogue utterances and the ontology terms, allowing the information to be shared across domains. The evaluation is performed on a recently collected multi-domain dialogues dataset, one order of magnitude larger than currently available corpora. Our model demonstrates great capability in handling multi-domain dialogues, simultaneously outperforming existing state-of-the-art models in single-domain dialogue tracking tasks.