Poster: ChatIYP: Enabling Natural Language Access to the Internet Yellow Pages Database

2025-09-23

AI Summary

This work addresses the challenge that non-expert users face in querying Internet Yellow Pages (IYP) graph databases. We propose ChatIYP, the first domain-adapted Retrieval-Augmented Generation (RAG) framework specifically designed for IYP. ChatIYP enables end-to-end natural language-to-graph query translation without requiring users to know Cypher syntax or the precise IYP schema, integrating retrieval-augmented generation, schema-aware Cypher query generation, and context-aware language modeling. Key contributions include: (1) an IYP-specific retrieval index and query optimization mechanism; and (2) an initial evaluation metric suite tailored for routing knowledge graph question answering. Experiments demonstrate high accuracy on simple query tasks and strong usability, validating the technical approach. ChatIYP establishes a reusable methodology and practical foundation for low-barrier access to network knowledge graphs.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Question Answering
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Agentic search
• Web Mining and Content Analysis: Community question answering

Abstract

The Internet Yellow Pages (IYP) aggregates information from multiple sources about Internet routing into a unified, graph-based knowledge base. However, querying it requires knowledge of the Cypher language and the exact IYP schema, thus limiting usability for non-experts. In this paper, we propose ChatIYP, a domain-specific Retrieval-Augmented Generation (RAG) system that enables users to query IYP through natural language questions. Our evaluation demonstrates solid performance on simple queries, as well as directions for improvement, and provides insights for selecting evaluation metrics that are better fit for IYP querying AI agents.

Problem

• Enabling natural language queries for Internet Yellow Pages database
• Eliminating the need for Cypher language expertise
• Improving usability of graph-based knowledge base for non-experts

Innovation

• Natural language querying for Internet Yellow Pages
• Domain-specific Retrieval-Augmented Generation system
• Graph-based knowledge base accessibility improvement