Candidate Attended Dialogue State Tracking Using BERT
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.
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
ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking
ReacTOD proposes a bounded neuro-symbolic architecture for zero-shot dialogue state tracking, using a self-correcting ReAct loop with deterministic validation. It achieves state-of-the-art results on MultiWOZ and Schema-Guided Dialogue benchmarks, improving joint goal accuracy by up to 14 percentage points.
Legal Domain Adaptation of Modern BERT Models
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.
Jointly Improving Dialect Identification and ASR in Indian Languages using Multimodal Feature Fusion
This paper proposes a multimodal framework that jointly improves Automatic Speech Recognition (ASR) and Dialect Identification (DID) for Indian languages, using a Bottleneck Encoder and RoBERTa with a gating mechanism. Evaluated on eight languages with 33 dialects, it achieves 81.63% DID accuracy and reduces CER/WER to 4.65%/17.73%.
DE-NER : Zero-shot Named Entity Recognition via Dialogue Elicitation of Large Language Models
Introduces DE-NER, a dialogue elicitation framework for zero-shot named entity recognition that uses self-play between questioner and roleplayer LLMs to clarify entity boundaries, achieving an average 3.75% F1 improvement over baselines.
The Word and the Way: Strategies for Domain-Specific BERT Pre-Training in German Medical NLP
This paper introduces ChristBERT, a family of domain-specific RoBERTa-based language models for German clinical NLP, and evaluates three domain adaptation strategies (continued pre-training, pre-training from scratch, and vocabulary adaptation) on medical named entity recognition and text classification tasks, achieving state-of-the-art results.