Candidate Attended Dialogue State Tracking Using BERT

arXiv cs.CL Papers

Summary

The paper presents a scalable framework for multi-domain dialogue state tracking using BERT, achieving zero-shot generalization and improving performance on the SGD dataset.

arXiv:2607.16021v1 Announce Type: new Abstract: Dialogue state tracking (DST) is one of the core components in task-oriented dialogue systems. At each turn in a conversation, DST estimates the user belief or dialogue state, which is used as input for downstream modules to predict system actions and generate responses. The increasingly popular dialogue system applications like Google Assistant, Siri and Alexa need to support a large number of services and APIs, resulting in growing attention to the scalability of such systems. Especially for some domains with little or no training data, the capability of transferring existing knowledge of other domains is highly desired. In this paper, we present a novel scalable framework for multi-domain dialogue state tracking. The proposed system leverages the pretrained BERT model to achieve zero-shot generalization, making it easy to quickly adapt to new domains without additional training. The performance of our model is evaluated on recently released schema-based dialogue (SGD) dataset, showing significant improvement compared to previous baseline.
Original Article
View Cached Full Text

Cached at: 07/20/26, 09:36 AM

# Candidate Attended Dialogue State Tracking Using BERT
Source: [https://arxiv.org/abs/2607.16021](https://arxiv.org/abs/2607.16021)
[View PDF](https://arxiv.org/pdf/2607.16021)

> Abstract:Dialogue state tracking \(DST\) is one of the core components in task\-oriented dialogue systems\. At each turn in a conversation, DST estimates the user belief or dialogue state, which is used as input for downstream modules to predict system actions and generate responses\. The increasingly popular dialogue system applications like Google Assistant, Siri and Alexa need to support a large number of services and APIs, resulting in growing attention to the scalability of such systems\. Especially for some domains with little or no training data, the capability of transferring existing knowledge of other domains is highly desired\. In this paper, we present a novel scalable framework for multi\-domain dialogue state tracking\. The proposed system leverages the pretrained BERT model to achieve zero\-shot generalization, making it easy to quickly adapt to new domains without additional training\. The performance of our model is evaluated on recently released schema\-based dialogue \(SGD\) dataset, showing significant improvement compared to previous baseline\.

## Submission history

From: Onkar Salvi \[[view email](https://arxiv.org/show-email/31dfe54e/2607.16021)\] **\[v1\]**Fri, 17 Jul 2026 14:56:55 UTC \(996 KB\)

Similar Articles

Legal Domain Adaptation of Modern BERT Models

arXiv cs.CL

This paper explores domain adaptation of ModernBERT models in the legal domain by further pre-training on US court opinions, achieving significant improvements over the vanilla model and releasing the checkpoints publicly.