How do I Build an NLG System: Requirements and Corpora
The key to success in building an NLG system is getting requirements right; this is true of software in general, and its true of NLG.
How do I Build an NLG System: Tools?
What are the best tools for building NLG systems?
Types of NLG Evaluation: Which is Right for Me?
A high-level discussion of the different ways of evaluating NLG systems.
How to do an NLG Evaluation: Human Ratings in Artificial Context
Advice on how to evaluate an NLG system by asking human subjects to rate the system, in an artificial experiment context (ie, not real world usage). This is the most common type of NLG evaluation
Evaluation in Medicine and NLG/NLP
Evaluation in NLP/NLG has a long way to go before it reaches the standards of hypothesis testing in clinical medicine
Text or Graphics?
Which is a better way to present information, text or graphics (information visualisation)?
Good Papers are Hard to Publish
Is it the case that important papers with major impact are *harder* to publish? This certainly seems to have been my experience
Commercial and Academic Perspectives on NLG (and AI?)
Perhaps not surprisingly, there are major differences in emphasis between commercial and academic work on NLG
NLG vs Templates: Levels of Sophistication in Generating Text
I dislike talking about “NLG” vs “templates” because these terms are poorly defined. I prefer to talk about five levels of sophistication in generating texts, which I describe in this post
The story of simplenlg
Simplenlg has evolved over 20 years from a set of Java classes I threw together for a project, into the most widely used open-source NLG package. In this blog I give a quick summary of its history.
