ITRI - 02 - 05 What is NLG ?
نویسندگان
چکیده
Giving an adequate general definition of the input to natural language generation (NLG), and hence to NLG itself, is a notoriously difficult problem, practically, theoretically and even methodologically. In this paper, we describe our recent experiences of implementing an NLG component of a larger question-answering system, and trying to understand and resolve some of these problems in this context. We examine the whole lifetime of an answer, from internal data structure to final expression as text, and look for characteristics of the processing which might help identify where NLG really begins. On the basis of this analysis we propose some principles to inform discussions on the scope of NLG as an individuated enterprise.
منابع مشابه
ITRI - 98 - 05 Multilingual authoring using feedback texts Richard Power and Donia
There are obvious reasons for trying to automate the production of multilingual documentation, especially for routine subjectmatter in restricted domains (e.g. technical instructions). Two approaches have been adopted: Machine Translation (MT) of a source text, and Multilingual Natural Language Generation (M-NLG) from a knowledge base. For MT, information extraction is a major difficulty, since...
متن کاملITRI-00-12 Natural Language Generation in the MILE System
We describe how Natural Language Generation (NLG) Technology is used in the MILE system. MILE is a web-based system for accessing maritime rules and regulations. We explain how the architecture of the system was derived from a set of user requirements and focus on the role of NLG in this architecture. More specifically, we describe how multilingual generation of answers to queries and the use o...
متن کامل