Dialog State Tracking Research Articles

ECDG-DST: A dialogue state tracking model based on efficient context and domain guidance for smart dialogue systems

ECDG-DST: A dialogue state tracking model based on efficient context and domain guidance for smart dialogue systems

Prompt-Based End-to-End Cross-Domain Dialogue State Tracking

Cross-domain dialogue state tracking (DST) focuses on using labeled data from source domains to train a DST model for target domains. It is of great significance for transferring a dialogue system into new domains. Most of the existing cross-domain DST models track each slot independently, which leads to poor performances caused by not considering the correlation among different slots, as well as low efficiency of training and inference. This paper, therefore, proposes a prompt-based end-to-end cross-domain DST method for efficiently tracking all slots simultaneously. A dynamic prompt template shuffle method is proposed to alleviate the bias of the slot order, and a dynamic prompt template sampling method is proposed to alleviate the bias of the slot number, respectively. The experimental results on the MultiWOZ 2.0 and MultiWOZ 2.1 datasets show that our approach consistently outperforms the state-of-the-art baselines in all target domains and improves both training and inference efficiency by at least 5 times.

Enhancing Task-Oriented Dialogue Modeling through Coreference-Enhanced Contrastive Pre-Training

Pre-trained language models (PLMs) are proficient at understanding context in plain text but often struggle with the nuanced linguistics of task-oriented dialogues. The information exchanges in dialogues and the dynamic role-shifting of speakers contribute to complex coreference and interlinking phenomena across multi-turn interactions. To address these challenges, we propose Coreference-Enhanced Contrastive Pre-training (CECPT), an innovative pre-training framework specifically designed to enhance dialogue modeling. CECPT utilizes unsupervised dialogue datasets to capture both semantic richness and structural coherence. Our experimental results demonstrate that the CECPT model significantly outperforms established baselines in three critical applications: intent recognition, dialogue act prediction, and dialogue state tracking. These findings suggest that CECPT is more adept at following the information flow within dialogues and accurately linking statuses to their respective references.

TCLNet: Turn-level contrastive learning network with reranking for dialogue state tracking

Dialogue state tracking (DST) plays a crucial role in task-oriented dialogue systems, as it interprets and tracks user intentions throughout the dialogue. The accuracy of DST directly impacts system efficiency and user experience. While existing generation-based DST models have shown promising results, effectively modelling long dialogue sequences remains a challenge. Furthermore, the greedy search decoding strategy employed by most previous works for speed is suboptimal because the probability of ground truth tokens is not always the highest. In this study, we propose a novel learning framework that addresses these issues by incorporating turn-level contrastive learning and a reranking module. Specifically, we adopt turn-level contrastive learning to progressively rectify the intermediate states of lengthy dialogues by contrasting data points at a finer granularity. Additionally, the integration of the reranking module empowers the model to make more reliable decisions at each time step by further considering alternative tokens with high probabilities. Experimental results demonstrate that our approach consistently enhances the model’s capability to handle long dialogue sequences and achieves superior performance over strong baselines on both the MultiWOZ 2.1 and MultiWOZ 2.2 datasets.

UTMGAT: a unified transformer with memory encoder and graph attention networks for multidomain dialogue state tracking

UTMGAT: a unified transformer with memory encoder and graph attention networks for multidomain dialogue state tracking

OSTOD: One-Step Task-Oriented Dialogue with activated state and retelling response

As of present, the progress of conversational AI research has been greatly propelled by large-scale pre-trained language models. In particular, task-oriented dialogue systems have gained widespread attention owing to their immense potential in helping individuals accomplish diverse objectives, such as booking hotels, making restaurant reservations, and purchasing train tickets. In the past, task-oriented dialogue systems were typically viewed as a multi-step process that included spoken language understanding, dialogue state tracking, dialogue policy learning, and natural language generation. More recently, large-scale pre-trained language models enables the development of end-to-end neural pipeline task-oriented dialogue systems, which combine multiple steps into a single model, allowing for joint optimization and preventing error propagation. However, in order to explicitly retrieve information from databases to ensure the interpretability of the system, almost all end-to-end neural pipeline methods inevitably require predicting dialogue state as an intermediate result specialized for the domain or task, which results in significant challenges for generalization. To solve the problem above, we propose One-Step Task-Oriented Dialogue (OSTOD) in this paper, which models task-oriented dialogue by synchronously generating activated states and retelling responses, where activated states refer to slot values that contribute to database access, and retelling responses are system responses that contain activated state information. Specifically, first, automatic methods are designed to build data containing activated states and retelling responses. Then, a joint generation model that synchronously predicts activated states and retelling responses in a single step is proposed for task-oriented dialogue modelling. Based on empirical results obtained from the MultiWOZ 2.0 and MultiWOZ 2.1 datasets, our OSTOD model demonstrates comparable performance to state-of-the-art baselines. Moreover, our model exhibits exceptional generalization capabilities in few-shot learning and domain transfer scenarios.

KddRES: A Multi-level Knowledge-driven Dialogue Dataset for Restaurant Towards Customized Dialogue System

To alleviate the shortage of dialogue datasets for Cantonese, one of the low-resource languages, and facilitate the development of customized task-oriented dialogue systems, we propose KddRES, the first Cantonese Knowledge-driven dialogue dataset for REStaurants. It contains 834 multi-turn dialogues, 8000 utterances, and 26 distinct slots. The slots are hierarchical, and beneath the 26 coarse-grained slots are the additional 16 fine-grained slots. Annotations of dialogue states and dialogue actions at both the user and system sides are provided to suit multiple downstream tasks such as natural language understanding and dialogue state tracking. To effectively detect hierarchical slots, we propose a framework HierBERT by modelling label semantics and relationships between different slots. Experimental results demonstrate that KddRES is more challenging compared with existing datasets due to the introduction of hierarchical slots and our framework is particularly effective in detecting secondary slots and achieving a new state-of-the-art. Given the rich annotation and hierarchical slot structure of KddRES, we hope it will promote research on the development of customized dialogue systems in Cantonese and other conversational AI tasks, such as dialogue state tracking and policy learning.

DSTEA: Improving Dialogue State Tracking via Entity Adaptive pre-training

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 toolkit, 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 results 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%). Comparative experiments considering various entity types and different entity adaptive pre-training configurations, such as masking strategy and masking rate, further validated the efficacy of DSTEA.

Multi-domain gate and interactive dual attention for multi-domain dialogue state tracking

Multi-domain dialogue state tracking (MDST) is a crucial component of task-oriented dialogue systems. In the context of multi-turn dialogues between the user and the system, MDST necessitates the continuous keeping track of dialogue states based on the information present in the current dialogue utterance and the dialogue states from the preceding turn. Recent work achieves the successful execution of multi-domain dialogue tasks by adopting an approach that treats each state as an individual label, while regrettably neglecting the potential benefits of incorporating domain-specific information associated with these states. Simultaneous, existing models exhibit a deficiency in effectively modelling the explicit correlations between dialogue contextual semantics and dialogue states. In this paper, we introduce the modules of multi-domain gate and interactive dual attention as novel solutions to address the aforementioned concerns. For the efficient exploitation of domain-specific information within states, we leverage the multi-domain gate as indices to amplify the states pertinent to the current utterance domain while filtering out irrelevant states. Interactive dual attention comprises utterance attention and slot attention, effectively modelling the correlation between dialogue utterances and slots. Additionally, interactive dual attention ensures that each dialogue utterance interacts with the slots once to derive all state updates, thereby ensuring computational efficiency. Specifically, slot attention models the associations between slots by incorporating semantic features to forecast updates in slot values. Meanwhile, utterance attention captures the semantics of dialogue context and integrates it with slot name features to generate dialogue states. All the aforementioned modules are designed based on a slot-independent framework, enabling efficient scalability of slots and circumventing issues related to model input limitations. The experimental results on the multi-domain dialogues dataset MultiWOZ 2.4 demonstrate the superior performance of our model compared to the baselines. Additionally, we conduct a comprehensive analysis of the effectiveness of the multi-domain gate and interactive dual attention modules, elucidating their contribution to the performance of the model through visualization and case studies.

A Stack-Propagation Framework With Slot Filling for Multi-Domain Dialogue State Tracking.

Dialogue state tracking (DST) is a core component of task-oriented dialogue systems. Recent works focus mainly on end-to-end DST models that omit the spoken language understanding (SLU) module to directly obtain the dialogue state based on a user's dialogue. However, the slot information detected by slot filling in SLU is closely tied to the slot-value pair that needs to be updated in DST. Efficient use of the key slot semantic knowledge obtained by slot filling contributes to improving the performance of DST. Based on this idea, we introduce slot filling as a subtask and build an end-to-end joint model to explicitly integrate the slot information detected by slot filling, which further guides DST. In this article, a novel stack-propagation framework with slot filling for multidomain DST is proposed. The stack-propagation framework is introduced to jointly model slot filling and DST. The framework directly feeds the key slot semantic knowledge detected by slot filling into the DST module. In addition, a slot-masked attention mechanism is designed to enable DST to focus on the key slot information obtained by slot filling. When the slot value is updated, a slot-value softcopy mechanism is designed to enhance the influence of the words marked by key slots. Experiments show that our approach outperforms previous methods and performs outstandingly on two benchmark datasets.

STN4DST: A Scalable Dialogue State Tracking Based on Slot Tagging Navigation

STN4DST: A Scalable Dialogue State Tracking Based on Slot Tagging Navigation

Injecting Linguistic Knowledge Into BERT for Dialogue State Tracking

Injecting Linguistic Knowledge Into BERT for Dialogue State Tracking

MGCRL: Multi-view graph convolution and multi-agent reinforcement learning for dialogue state tracking

MGCRL: Multi-view graph convolution and multi-agent reinforcement learning for dialogue state tracking

Cross-domain coreference modeling in dialogue state tracking with prompt learning

Dialogue state tracking (DST) is to identify user goals from dialogue context and it is an essential component in task-oriented dialogue systems. In multi-domain task-oriented dialogues, a user often refers to the information mentioned in the previous context when the topic is transferred to another domain. Accurate modeling of the cross-domain coreference plays an important role in building qualified DST systems. As far as we know, there is only one work attempting to model the cross-domain coreference phenomenon in DST. However, it still has low efficiency and suffers from the difficulty of handling the complex reasoning over the dialogue context. To tackle these problems, in this paper, we propose a simple but effective DST model, called Coref-DST, to track the cross-domain coreference slots. Instead of predicting the actual values via complex reasoning, Coref-DST directly identifies the coreferred domains and slots from the dialogue context. Moreover, a domain-specific prompt method is proposed to predict all the slot values in a domain simultaneously, so as to better capture the relationship among the slots. The extensive experimental results on the MultiWOZ 2.3 dataset demonstrate that Coref-DST not only outperforms the state-of-the-art DST baselines but also has higher efficiency of training and inference.

The task-oriented Smart Tourism Chatbot Service

The smart tourism service provides tourists with a travel planner service before the trip and a tour guide service during the trip. Smart tourism chatbot service can easily and conveniently provide smart tourism services to tourists along with smart tourism apps. In this paper, we develop the smart tourism platform and propose the task-oriented smart tourism chatbot service that efficiently provides tourism information provided by smart tourism apps to users. The smart tourism platform consists of the smart tourism chatbot and smart tourism information systems. The smart tourism chatbot system identifies the intention of the user's question and searches for the tourism information ID in the tourism information knowledgebase. The smart tourism information system provides tourism information of the smart tourism app to the user using the searched tourism information ID. The proposed smart tourism chatbot system applies the tourism information NER (Named Entity Recognition) model to accurately understand the intention of the user's question to the existing DST (Dialogue State Tracking) model-based chatbot system. We create tourist information named entities of the NER model based on the values of the domain and slot in the DST model defined in the 4W1H method. The NER model determines the domain, slot, and value to identify the intention of the user's question, and the DST model manages the dialogue state and retrieves the tourism information ID from the tourism information knowledgebase.

Mutually improved response generation and dialogue summarization for multi-domain task-oriented dialogue systems

With the development of pre-trained language models (PrLM), the research of PrLM-based multi-domain task-oriented dialogue systems (TOD) has attracted growing attention and has achieved great progress. However, most current studies suffer from two problems. First, they model dialogue state tracking as an independent subtask supervised by slot-value pairs, resulting in poor adaptability when transferring to new task domains. Second, these studies ignore the fact that not all dialogue histories are valuable for the ensuing turns as they increase in length. To tackle these two issues, we propose a simple and novel framework to explore multi-domain TOD by jointly training response generation and dialogue summarization with PrLM as the backbone. Specifically, first, we use fluent text generated by the dialogue summarization model to replace formatted dialogue states, treating the dialogue state identification task as a natural language generation task, which allows dialogue state tracking to be easily extended to new task domains. Second, dialogue summarization removes redundant and useless information from the current dialogue process and is fed into the response decoder enabling the system to focus on crucial details in long dialogues. Furthermore, we employ a dialogue chunk detector to assist the dialogue summarization model and design a fusion mechanism to dynamically integrate helpful dialogue summarization into the response generation process. Experimental results show that the proposed model achieves state-of-the-art performance in both automatic and human evaluations on two public datasets and demonstrate that the joint framework can benefit both tasks from each other.

External Slot Relationship Memory for Multi-Domain Dialogue State Tracking

Dialogue state tracking is an essential component in multi-domain dialogue systems that aims to accurately determine the current dialogue state based on the dialogue history. Existing research has addressed the issue of multiple mappings in dialogues by employing slot self-attention as a data-driven approach. However, learning the relationships between slots from a single sample often has limitations and may introduce noise and have high time complexity issues. In this paper, we propose an external slot relation memory-based dialogue state tracking model (ER-DST). By utilizing external memory storage, we learn the relationships between slots as a dictionary of multi-domain slot relations. Additionally, we employ a small filter to discard slot information irrelevant to the current dialogue state. Our method is evaluated on MultiWOZ 2.0 and MultiWOZ 2.1, achieving improvements of 0.23% and 0.39% over the baseline models, respectively, while reducing the complexity of the slot relationship learning component to O(n).

Unsupervised Dialogue State Tracking for End-to-End Task-Oriented Dialogue with a Multi-Span Prediction Network

Unsupervised Dialogue State Tracking for End-to-End Task-Oriented Dialogue with a Multi-Span Prediction Network

Dialogue State Distillation Network with Inter-slot Contrastive Learning for Dialogue State Tracking

In task-oriented dialogue systems, Dialogue State Tracking (DST) aims to extract users' intentions from the dialogue history. Currently, most existing approaches suffer from error propagation and are unable to dynamically select relevant information when utilizing previous dialogue states. Moreover, the relations between the updates of different slots provide vital clues for DST. However, the existing approaches rely only on predefined graphs to indirectly capture the relations. In this paper, we propose a Dialogue State Distillation Network (DSDN) to utilize relevant information of previous dialogue states and migrate the gap of utilization between training and testing. Thus, it can dynamically exploit previous dialogue states and avoid introducing error propagation simultaneously. Further, we propose an inter-slot contrastive learning loss to effectively capture the slot co-update relations from dialogue context. Experiments are conducted on the widely used MultiWOZ 2.0 and MultiWOZ 2.1 datasets. The experimental results show that our proposed model achieves the state-of-the-art performance for DST.

Learning to Imagine: Distillation-Based Interactive Context Exploitation for Dialogue State Tracking

In dialogue state tracking (DST), the exploitation of dialogue history is a crucial research direction, and the existing DST models can be divided into two categories: full-history models and partial-history models. Since the “select first, use later” mechanism explicitly filters the distracting information being passed to the downstream state prediction, the partial-history models have recently achieved a performance advantage over the full-history models. However, besides the redundant information, some critical dialogue context information was inevitably filtered out by the partial-history models simultaneously. To reconcile the contextual consideration with avoiding the introduction of redundant information, we propose DICE-DST, a model-agnostic module widely applicable to the partial-history DST models, which aims to strengthen the ability of context exploitation for the encoder of each DST model. Specifically, we first construct a teacher encoder and devise two contextual reasoning tasks to train it to acquire extensive dialogue contextual knowledge. Then we transfer the contextual knowledge from the teacher encoder to the student encoder via a novel turn-level attention-alignment distillation. Experimental results show that our approach extensively improves the performance of partial-history DST models and thereby achieves new state-of-the-art performance on multiple mainstream datasets while keeping high efficiency.