Summary of Hiertod: a Task-oriented Dialogue System Driven by Hierarchical Goals, By Lingbo Mo et al.
HierTOD: A Task-Oriented Dialogue System Driven by Hierarchical Goals
by Lingbo Mo, Shun Jiang, Akash Maharaj, Bernard Hishamunda, Yunyao Li
First submitted to arxiv on: 11 Nov 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper introduces HierTOD, a Task-Oriented Dialogue (TOD) system designed to assist users in completing complex tasks in enterprise environments. Unlike traditional TOD systems, which rely on a single-layered workflow structure, HierTOD is driven by hierarchical goals and can support composite workflows. This allows it to facilitate mixed-initiative dialogue and improve task completion. The system includes components for natural language understanding, goal retrieval, dialogue management, and response generation, backed by a well-organized data service with domain knowledge base and retrieval engine. HierTOD unifies two TOD paradigms: slot-filling for information collection and step-by-step guidance for task execution. A human study demonstrates the effectiveness and helpfulness of HierTOD in performing both paradigms. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary HierTOD is a special kind of computer system that helps people complete tasks by talking to them. Right now, these systems are good at helping with simple things like booking a hotel room. But when it comes to more complex tasks that require lots of specific knowledge, they can get stuck. The HierTOD system tries to fix this problem by using a new way of organizing its goals and workflows. This lets it have more helpful conversations with users and make it easier for them to complete their tasks. |
Keywords
» Artificial intelligence » Knowledge base » Language understanding
