Improving Longer-range Dialogue State Tracking
- URL: http://arxiv.org/abs/2103.00109v1
- Date: Sat, 27 Feb 2021 02:44:28 GMT
- Title: Improving Longer-range Dialogue State Tracking
- Authors: Ye Zhang, Yuan Cao, Mahdis Mahdieh, Jefferey Zhao, Yonghui Wu
- Abstract summary: Dialogue state tracking (DST) is a pivotal component in task-oriented dialogue systems.
In this paper, we aim to improve the overall performance of DST with a special focus on handling longer dialogues.
- Score: 22.606650177804966
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Dialogue state tracking (DST) is a pivotal component in task-oriented
dialogue systems. While it is relatively easy for a DST model to capture belief
states in short conversations, the task of DST becomes more challenging as the
length of a dialogue increases due to the injection of more distracting
contexts. In this paper, we aim to improve the overall performance of DST with
a special focus on handling longer dialogues. We tackle this problem from three
perspectives: 1) A model designed to enable hierarchical slot status
prediction; 2) Balanced training procedure for generic and task-specific
language understanding; 3) Data perturbation which enhances the model's ability
in handling longer conversations. We conduct experiments on the MultiWOZ
benchmark, and demonstrate the effectiveness of each component via a set of
ablation tests, especially on longer conversations.
Related papers
- Chain of Thought Explanation for Dialogue State Tracking [52.015771676340016]
Dialogue state tracking (DST) aims to record user queries and goals during a conversational interaction.
We propose a model named Chain-of-Thought-Explanation (CoTE) for the DST task.
CoTE is designed to create detailed explanations step by step after determining the slot values.
arXiv Detail & Related papers (2024-03-07T16:59:55Z) - OLISIA: a Cascade System for Spoken Dialogue State Tracking [1.6655682083533425]
OLISIA is a cascade system which integrates an Automatic Speech Recognition (ASR) model and a Dialogue State Tracking (DST) model.
We introduce several adaptations in the ASR and DST modules to improve integration and robustness to spoken conversations.
We conduct an in-depth analysis of the results and find that normalizing the ASR outputs and adapting the DST inputs through data augmentation, along with increasing the pre-trained models size all play an important role in reducing the performance discrepancy between written and spoken conversations.
arXiv Detail & Related papers (2023-04-20T09:30:50Z) - Stabilized In-Context Learning with Pre-trained Language Models for Few
Shot Dialogue State Tracking [57.92608483099916]
Large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks.
For more complex tasks such as dialogue state tracking (DST), designing prompts that reliably convey the desired intent is nontrivial.
We introduce a saliency model to limit dialogue text length, allowing us to include more exemplars per query.
arXiv Detail & Related papers (2023-02-12T15:05:10Z) - KILDST: Effective Knowledge-Integrated Learning for Dialogue State
Tracking using Gazetteer and Speaker Information [3.342637296393915]
Dialogue State Tracking (DST) is core research in dialogue systems and has received much attention.
It is necessary to define a new problem that can deal with dialogue between users as a step toward the conversational AI that extracts and recommends information from the dialogue between users.
We introduce a new task - DST from dialogue between users about scheduling an event (DST-S)
The DST-S task is much more challenging since it requires the model to understand and track dialogue in the dialogue between users and to understand who suggested the schedule and who agreed to the proposed schedule.
arXiv Detail & Related papers (2023-01-18T07:11:56Z) - OPAL: Ontology-Aware Pretrained Language Model for End-to-End
Task-Oriented Dialogue [40.62090743056549]
This paper presents an ontology-aware pretrained language model (OPAL) for end-to-end task-oriented dialogue (TOD)
Unlike chit-chat dialogue models, task-oriented dialogue models fulfill at least two task-specific modules: dialogue state tracker (DST) and response generator (RG)
arXiv Detail & Related papers (2022-09-10T04:38:27Z) - A Multi-Task BERT Model for Schema-Guided Dialogue State Tracking [78.2700757742992]
Task-oriented dialogue systems often employ a Dialogue State Tracker (DST) to successfully complete conversations.
Recent state-of-the-art DST implementations rely on schemata of diverse services to improve model robustness.
We propose a single multi-task BERT-based model that jointly solves the three DST tasks of intent prediction, requested slot prediction and slot filling.
arXiv Detail & Related papers (2022-07-02T13:27:59Z) - In-Context Learning for Few-Shot Dialogue State Tracking [55.91832381893181]
We propose an in-context (IC) learning framework for few-shot dialogue state tracking (DST)
A large pre-trained language model (LM) takes a test instance and a few annotated examples as input, and directly decodes the dialogue states without any parameter updates.
This makes the LM more flexible and scalable compared to prior few-shot DST work when adapting to new domains and scenarios.
arXiv Detail & Related papers (2022-03-16T11:58:24Z) - Dialogue Summaries as Dialogue States (DS2), Template-Guided
Summarization for Few-shot Dialogue State Tracking [16.07100713414678]
Few-shot dialogue state tracking (DST) is a realistic solution to this problem.
We propose to reformulate dialogue state tracking as a dialogue summarization problem.
arXiv Detail & Related papers (2022-03-03T07:54:09Z) - Improving Limited Labeled Dialogue State Tracking with Self-Supervision [91.68515201803986]
Existing dialogue state tracking (DST) models require plenty of labeled data.
We present and investigate two self-supervised objectives: preserving latent consistency and modeling conversational behavior.
Our proposed self-supervised signals can improve joint goal accuracy by 8.95% when only 1% labeled data is used.
arXiv Detail & Related papers (2020-10-26T21:57:42Z) - Dual Learning for Dialogue State Tracking [44.679185483585364]
Dialogue state tracking (DST) is to estimate the dialogue state at each turn.
Due to the dependency on complicated dialogue history contexts, DST data annotation is more expensive than single-sentence language understanding.
We propose a novel dual-learning framework to make full use of unlabeled data.
arXiv Detail & Related papers (2020-09-22T10:15:09Z) - TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented
Dialogue [113.45485470103762]
In this work, we unify nine human-human and multi-turn task-oriented dialogue datasets for language modeling.
To better model dialogue behavior during pre-training, we incorporate user and system tokens into the masked language modeling.
arXiv Detail & Related papers (2020-04-15T04:09:05Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.