A system for the semiautomatic generation of E-R models from natural language specifications
Data & Knowledge Engineering
Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project
Building Large Knowledge-Based Systems; Representation and Inference in the Cyc Project
Transformation of Requirement Specifications Expressed in Natural Language into an EER Model
ER '93 Proceedings of the 12th International Conference on the Entity-Relationship Approach: Entity-Relationship Approach
Scaling up. Using the WWW to Resolve PP Attachment Ambiguities
KONVENS 2000 / Sprachkommunikation, Vorträge der gemeinsamen Veranstaltung 5. Konferenz zur Verarbeitung natürlicher Sprache (KONVENS), 6. ITG-Fachtagung "Sprachkommunikation"
Extracting Biochemical Interactions from MEDLINE Using a Link Grammar Parser
ICTAI '03 Proceedings of the 15th IEEE International Conference on Tools with Artificial Intelligence
Database Design Using Entity-Relationship Diagrams
Database Design Using Entity-Relationship Diagrams
Using the web to obtain frequencies for unseen bigrams
Computational Linguistics - Special issue on web as corpus
Acquisition of conceptual data models from natural language descriptions
EACL '87 Proceedings of the third conference on European chapter of the Association for Computational Linguistics
ConceptNet — A Practical Commonsense Reasoning Tool-Kit
BT Technology Journal
Database design tools: an expert system approach
VLDB '85 Proceedings of the 11th international conference on Very Large Data Bases - Volume 11
Flexible and customizable NL representation of requirements for ETL processes
NLDB'07 Proceedings of the 12th international conference on Applications of Natural Language to Information Systems
| Hi-index | 0.00 |
This paper describes a natural language system that extracts entity relationship diagram components from natural language database design documents. The system is a fully integrated composite of existing, publicly available components including a parser, WordNet and Google web corpus search facilities, and a novel rule-based tuple-extraction process. The system differs from previous approaches in being fully automatic (as opposed to approaches requiring human disambiguation or other interaction) and in providing a higher level of performance than previously reported results.