paper-with-me

Papers

ThingTalk: An Extensible, Executable Representation Language for Task-Oriented Dialogues

2022-03-23 · Monica S. Lam, Giovanni Campagna, Mehrad Moradshahi, Sina J. Semnani, Silei Xu

Task-oriented conversational agents rely on semantic parsers to translate natural language to formal representations. In this paper, we propose the design and rationale of the ThingTalk formal representation, and how the design improves the development of transactional task-oriented agents. ThingTalk is built on four core principles: (1) representing user requests directly as executable statements, covering all the functionality of the agent, (2) representing dialogues formally and succinctly to support accurate contextual semantic parsing, (3) standardizing types and interfaces to maximize reuse between agents, and (4) allowing multiple, independently-developed agents to be composed in a single virtual assistant. ThingTalk is developed as part of the Genie Framework that allows developers to quickly build transactional agents given a database and APIs. We compare ThingTalk to existing representations: SMCalFlow, SGD, TreeDST. Compared to the others, the ThingTalk design is both more general and more cost-effective. Evaluated on the MultiWOZ benchmark, using ThingTalk and associated tools yields a new state of the art accuracy of 79% turn-by-turn.

📄 PDF Abstract BibTeX arXiv:2203.12751

Code (1)

stanford-oval/genie-toolkit 공식 구현 pytorch

Tasks

Semantic Parsing

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk+ Representation

2021-09-17 · ACL ARR September 2021 9 · Anonymous

Previous attempts to build effective semantic parsers for Wizard-of-Oz (WOZ) conversations suffer from the difficulty in acquiring a high-quality, manually annotated training set. Approaches based only on dialogue synthe…

A Few-Shot Semantic Parser for Wizard-of-Oz Dialogues with the Precise ThingTalk Representation

2020-09-16 · Findings (ACL) 2022 5 · Giovanni Campagna, Sina J. Semnani, Ryan Kearns, Lucas Jun Koba Sato 외

Previous attempts to build effective semantic parsers for Wizard-of-Oz (WOZ) conversations suffer from the difficulty in acquiring a high-quality, manually annotated training set. Approaches based only on dialogue synthe…

Data AugmentationDialogue State Tracking

Grounding Open-Domain Instructions to Automate Web Support Tasks

2021-03-30 · NAACL 2021 4 · Nancy Xu, Sam Masling, Michael Du, Giovanni Campagna 외

Grounding natural language instructions on the web to perform previously unseen tasks enables accessibility and automation. We introduce a task and dataset to train AI agents from open-domain, step-by-step instructions o…

What Makes AI Research Replicable? Executable Knowledge Graphs as Scientific Knowledge Representations

2025-10-20 · Yujie Luo, Zhuoyun Yu, Xuehai Wang, Yuqi Zhu 외 arxiv

Replicating AI research is a crucial yet challenging task for large language model (LLM) agents. Existing approaches often struggle to generate executable code, primarily due to insufficient background knowledge and the …

Knowledge Graphs

Y-BotFrame: An Extensible Embodied Agent Framework for Quadruped Robot Assistants

2026-06-11 · Luyao Zhang, Ke Li, Yuan Ding, Xulong Zhao 외 arxiv

Quadruped robots are capable of traversing a wide range of complex terrains with high flexibility. As highly mobile ground-based intelligent platforms, they can be equipped with modules for navigation control, environmen…