AnyTOD: A Programmable Task-Oriented Dialog System

• URL: http://arxiv.org/abs/2212.09939v1
• Date: Tue, 20 Dec 2022 01:23:01 GMT
• Title: AnyTOD: A Programmable Task-Oriented Dialog System
• Authors: Jeffrey Zhao, Yuan Cao, Raghav Gupta, Harrison Lee, Abhinav Rastogi, Mingqiu Wang, Hagen Soltau, Izhak Shafran, Yonghui Wu
• Abstract summary: We propose AnyTOD, an end-to-end task-oriented dialog (TOD) system with zero-shot capability for unseen tasks. We demonstrate state-of-the-art results on the STAR and ABCD benchmarks, as well as AnyTOD's strong zero-shot transfer capability in low-resource settings.
• Score: 26.387269876540348
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose AnyTOD, an end-to-end task-oriented dialog (TOD) system with zero-shot capability for unseen tasks. We view TOD as a program executed by a language model (LM), where program logic and ontology is provided by a designer in the form of a schema. To enable generalization onto unseen schemas and programs without prior training, AnyTOD adopts a neuro-symbolic approach. A neural LM keeps track of events that occur during a conversation, and a symbolic program implementing the dialog policy is executed to recommend next actions AnyTOD should take. This approach drastically reduces data annotation and model training requirements, addressing a long-standing challenge in TOD research: rapidly adapting a TOD system to unseen tasks and domains. We demonstrate state-of-the-art results on the STAR and ABCD benchmarks, as well as AnyTOD's strong zero-shot transfer capability in low-resource settings. In addition, we release STARv2, an updated version of the STAR dataset with richer data annotations, for benchmarking zero-shot end-to-end TOD models.

Related papers

• TOD-Flow: Modeling the Structure of Task-Oriented Dialogues [77.15457469745364]
  We propose a novel approach focusing on inferring the TOD-Flow graph from dialogue data annotated with dialog acts. The inferred TOD-Flow graph can be easily integrated with any dialogue model to improve its prediction performance, transparency, and controllability.
  arXiv  Detail & Related papers  (2023-12-07T20:06:23Z)
• InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems [60.53276524369498]
  Large language models (LLMs) have been used for diverse tasks in natural language processing (NLP) We present InstructTODS, a novel framework for zero-shot end-to-end task-oriented dialogue systems. InstructTODS generates a proxy belief state that seamlessly translates user intentions into dynamic queries.
  arXiv  Detail & Related papers  (2023-10-13T06:36:26Z)
• SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting [43.02058641501056]
  Large language models (LLMs) have demonstrated exceptional proficiency in conversational engagement. We introduce SGP-TOD,Guided Prompting for building Task-Oriented Dialog systems effortlessly. SGP-TOD comprises three components: a LLM for engaging with users, a DST Prompter to aid the LLM with dialog state tracking, and a Policy Prompter to elicit proper responses adhering to the provided dialog policy.
  arXiv  Detail & Related papers  (2023-05-15T23:29:56Z)
• Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema [2.7178968279054936]
  State-of-the-art approaches in task-oriented dialog systems formulate the problem as a conditional sequence generation task. This requires labeled training data for each new domain or task. We introduce a novel Zero-Shot generalizable end-to-end Task-oriented Dialog system, ZS-ToD.
  arXiv  Detail & Related papers  (2023-03-28T18:56:31Z)
• Enhancing Task Bot Engagement with Synthesized Open-Domain Dialog [89.35658776144638]
  It is essential to build a system that can handle both TOD and ODD and access different knowledge sources. We propose a framework for automatically generating dialogues that combine knowledge-grounded ODDs and TODs in various settings. We introduce a unified model PivotBot that is capable of appropriately adopting TOD and ODD modes and accessing different knowledge sources.
  arXiv  Detail & Related papers  (2022-12-20T05:51:47Z)
• 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)
• Description-Driven Task-Oriented Dialog Modeling [29.200221289845533]
  We show that a language description-driven system exhibits better understanding of task specifications, higher performance on state tracking, improved data efficiency, and effective zero-shot transfer to unseen tasks. We present a simple yet effective Description-Driven Dialog State Tracking (D3ST) model, which relies purely on schema descriptions and an "index-picking" mechanism.
  arXiv  Detail & Related papers  (2022-01-21T22:07:41Z)
• Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System [26.837972034630003]
  PPTOD is a unified plug-and-play model for task-oriented dialogue. We extensively test our model on three benchmark TOD tasks, including end-to-end dialogue modelling, dialogue state tracking, and intent classification.
  arXiv  Detail & Related papers  (2021-09-29T22:02:18Z)
• CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems [56.302581679816775]
  This paper proposes Comprehensive Instruction (CINS) that exploits PLMs with task-specific instructions. We design a schema (definition, constraint, prompt) of instructions and their customized realizations for three important downstream tasks in ToD. Experiments are conducted on these ToD tasks in realistic few-shot learning scenarios with small validation data.
  arXiv  Detail & Related papers  (2021-09-10T03:23:06Z)
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems [75.87418236410296]
  We introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. RADDLE is designed to favor and encourage models with a strong generalization ability. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain.
  arXiv  Detail & Related papers  (2020-12-29T08:58:49Z)

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.