“Do you follow me?”: A Survey of Recent Approaches in Dialogue State Tracking

@inproceedings{Jacqmin2022DoYF,
  title={“Do you follow me?”: A Survey of Recent Approaches in Dialogue State Tracking},
  author={L{\'e}o Jacqmin and Lina Maria Rojas-Barahona and Benoit Favre},
  booktitle={SIGDIAL Conferences},
  year={2022}
}
While communicating with a user, a task-oriented dialogue system has to track the user’s needs at each turn according to the conversation history. This process called dialogue state tracking (DST) is crucial because it directly informs the downstream dialogue policy. DST has received a lot of interest in recent years with the text-to-text paradigm emerging as the favored approach. In this review paper, we first present the task and its associated datasets. Then, considering a large number of… 
[PDF] Semantic Reader
5 Citations
Highly Influential Citations
1
Background Citations
4
Methods Citations
2

Figures and Tables from this paper

5 Citations

DiSTRICT: Dialogue State Tracking with Retriever Driven In-Context Tuning

DiSTRICT is proposed, a generalizable in-context tuning approach for DST that retrieves highly relevant training examples for a given dialogue to fine-tune the model without any hand-crafted templates, thereby providing an important advantage for real-world deployments that often have limited resource availability.

Span-prediction of Unknown Values for Long-sequence Dialogue State Tracking

This study proposes a new approach that uses a span-tokenizer and adds the Bi-LSTM layer on top of the BERT model to predict the exact span of multi-word values and shows that this strategy has led to a 1.80% improvement in the joint-goal accuracy and 0.15% improved in the slot accuracy metrics over the MultiWOZ 2.1 dataset compared to the SAVN model.

A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding

This work investigates the understanding ability of ChatGPT for zero-shot dialogue understanding tasks including spoken language understanding (SLU) and dialogue state tracking (DST).

Improving Dialogue Act Recognition with Augmented Data

This work is motivated by the limitations of current dialog act datasets, and the need to adapt for new domains as well as ambiguity in utterances written by humans, and shows that synthetic data, which is linguistically varied, can be very useful towards this goal.

Who's in Charge? Roles and Responsibilities of Decision-Making Components in Conversational Robots

It is argued that architectures placing ``action managers'' and ``interaction managers" on an equal footing may provide the best path forward for future human-robot interaction systems.

103 References

Recent Neural Methods on Dialogue State Tracking for Task-Oriented Dialogue Systems: A Survey

This paper aims at providing a comprehensive overview of recent developments in dialogue state tracking (DST) for task-oriented conversational systems, showing a significant increase of multiple domain methods, most of them utilizing pre-trained language models.

Improving Longer-range Dialogue State Tracking

This paper aims to improve the overall performance of DST with a special focus on handling longer dialogues, and addresses the problem from three perspectives: A model designed to enable hierarchical slot status prediction; a Balanced training procedure for generic and task-specific language understanding; and data perturbation which enhances the model’s ability in handling longer conversations.

What Did You Say? Task-Oriented Dialog Datasets Are Not Conversational!?

This work outlines a taxonomy of conversational and contextual effects, which is used to examine MultiWOZ, SGD and SMCalFlow, among the most recent and widely used task-oriented dialog datasets, and outlines desiderata for truly conversational dialog datasets.

“How Robust R U?”: Evaluating Task-Oriented Dialogue Systems on Spoken Conversations

This work presents a new benchmark on spoken task-oriented conversations, which is intended to study multi-domain dialogue state tracking and knowledge-grounded dialogue modeling and observes improvements in task performances when leveraging $n$-best speech recognition hypotheses such as by combining predictions based on individual hypotheses.

Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems

The Action-Based Conversations Dataset (ABCD), a fully-labeled dataset with over 10K human-to-human dialogues containing 55 distinct user intents requiring unique sequences of actions constrained by policies to achieve task success, is introduced.

Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Tracking

It is hypothesized that dialogue summaries are essentially unstructured dialogue states; hence, it is proposed to reformulate dialogue state tracking as a dialogue summarization problem, and the method DS2 outperforms previous works on few-shot DST in MultiWoZ 2.0 and 2.1.

Effective Sequence-to-Sequence Dialogue State Tracking

It is demonstrated that the choice of pre-training objective makes a significant difference to the state tracking quality and it is found that masked span prediction is more effective than auto-regressive language modeling for dialogue state tracking.

Slot Self-Attentive Dialogue State Tracking

This paper proposes a slot self-attention mechanism that can learn the slot correlations automatically, and achieves state-of-the-art performance on both datasets, verifying the necessity and effectiveness of taking slot correlations into consideration.

A Sequence-to-Sequence Approach to Dialogue State Tracking

A new approach to dialogue state tracking, referred to as Seq2Seq-DU, which formalizes DST as a sequence-to-sequence problem and outperforms the existing methods.

Beyond the Granularity: Multi-Perspective Dialogue Collaborative Selection for Dialogue State Tracking

DiCoS-DST is devised to dynamically select the relevant dialogue contents corresponding to each slot for state updating, and achieves new state-of-the-art performance on MultiWOZ 2.1 and Multi woz 2.2.
...