Fast, scalable and reliable generation of controlled natural language

Authors:
David Hardcastle;Richard Power
Affiliations:
The Open University, Milton Keynes, UK;The Open University, Milton Keynes, UK
Venue:
SETQA-NLP '08 Software Engineering, Testing, and Quality Assurance for Natural Language Processing
Year:
2008

Citing 7
Cited 1

Document structure

Computational Linguistics
The description logic handbook: theory, implementation, and applications

The description logic handbook: theory, implementation, and applications
Multilingual authoring using feedback texts

COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Cooking up referring expressions

ACL '89 Proceedings of the 27th annual meeting on Association for Computational Linguistics
XTAG system: a wide coverage grammar for English

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
Comlex Syntax: building a computational lexicon

COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 1
A support tool for writing multilingual instructions

IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2

Towards a generation-based semantic web authoring tool

ENLG '09 Proceedings of the 12th European Workshop on Natural Language Generation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we describe a natural language generation system which takes as its input a set of assertions encoded as a semantic graph and outputs a data structure connecting the semantic graph to a text which expresses those assertions, encoded as a TAG syntactic tree. The scope of the system is restricted to controlled natural language, and this allows the generator to work within a tightly restricted domain of locality. We can exploit this feature of the system to ensure fast and efficient generation, and also to make the generator reliable by providing a rapid algorithm which can exhaustively test at compile time the completeness of the linguistic resources with respect to the range of potential meanings. The system can be exported for deployment with a minimal build of the semantic and linguistic resources that is verified to ensure that no run-time errors will result from missing resources. The framework is targeted at using natural language generation technology to build semantic web applications where machine-readable information can be automatically expressed in natural language on demand.