Generation that exploits corpus-based statistical knowledge
Proceedings of the 17th international conference on Computational linguistics -Published 1 January 1998Open access
Irene Langkilde, Kevin Knight
Citations92
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
Abstract
We describe novel aspects of a new natural language generator called Nitrogen. This generator has a highly flexible input representation that allows a spectrum of input from syntactic to semantic depth, and shifts the burden of many linguistic decisions to the statistical post-processor. The generation algorithm is compositional, making it efficient, yet it also handles non-compositional aspects of language. Nitrogen's design makes it robust and scalable, operating with lexicons and knowledge bases of one hundred thousand entities.
Keywords
Computer ScienceBiochemistry, Genetics and Molecular Biology
arXiv (Cornell University)Building a Large-Scale Knowledge Base for Machine Translation
185 Citations1994Kevin Knight, Steve K. Luk
This paper focuses on the construction of a large ontology (or knowledge base, or world model) for supporting KBMT, which contains representations for some 70,000 commonly encountered objects, processes, qualities, and relations.
Two-level, many-paths generation
116 Citations1995Kevin Knight, Vasileios Hatzivassiloglou
A hybrid generator is built, in which gaps in symbolic knowledge are filled by statistical methods, to attack problems of large-scale natural language generation and to simplify current generators and enhance their portability.
A semantic-head-driven generation algorithm for unification-based formalisms
87 Citations1989Stuart M. Shieber, Gertjan van Noord +2 more
An algorithm for generating strings from logical form encodings that improves upon previous algorithms in that it places fewer restrictions on the class of grammars to which it is applicable, yet unlike topdown methods, it also permits left-recursion.
Lecture notes in computer scienceControlling content realization with functional unification grammars
62 Citations1992Michael Elhadad, Jacques Robin
Standard Functional Unification Grammars provide a structurally guided top-down control regime for sentence generation but this regime is no longer appropriate for two reasons: the unification of non-lexicalized semantic input with an integrated lexico-grammar and lexical choice.
FUF: the Universal Unifier User Manual Version 2.0
46 Citations1989Michael Elhadad
This document is the user manual for FUF version 5.2, a natural language generator program that uses the technique of unification grammars, and includes novel techniques in the unification allowing the specification of types and the expression of complete information.
SURGE: a Comprehensive Plug-in Syntactic Realization Component for Text Generation
7 Citations1998Michael Elhadad, Jacques Robin