From NLG Systems Wiki

Jump to: navigation, search


  • System Name: FERGUS
  • Short Description: Flexible Empiricist/Rationalist Generation Using Syntax
  • System Builders: Bangalore, Rambow[1][2][3][4]
  • Development Period: 2000–2002
  • Languages: English
  • Domain: independent
  • Theoretical framework: statistical


Extends statistically guided generation using n-grams with a tree-based statistical model as well as a traditional tree-based syntactic grammar based on the wide coverage XTAG grammar


  1. Bangalore, S., & Rambow, O. (2000). Exploiting a probabilistic hierarchical model for generation. Paper presented at Proceedings of the 18th Conference on Computational Linguistics (COLING'2000), July 31 - August 4 2000, Universität des Saarlandes, Saarbrücken, Germany. Bib
  2. Bangalore, S., Alshawi, H., & Douglas, S. (2000). Learning dependency translation models as collections of finite state head transducers. Computational Linguistics, 26(1). Bib
  3. Bangalore, S., Rambow, O., & Whitaker, S. (2000). Evaluation metrics for generation. Paper presented at Proceedings of the International Natural Language Generation Conference (INLG-2000), Mitzpe Ramon, Israel. Bib
  4. Bangalore, S., & Rambow, O. (2000). Corpus-based lexical choice in natural language generation. Paper presented at Proceedings of the Association for Computational Linguistics meeting, Hong Kong. Bib
Facts about FERGUSRDF feed
DescriptionFlexible Empiricist/Rationalist Generation Using Syntax  +
Domainindependent  +
Ended2002  +
FrameworkStatistical  +
LanguageEnglish  +
Started2000  +
WorkerBangalore  +, and Rambow  +
Personal tools