Product Descriptions
The most talked about NLG application at INLG was product descriptions. Which are very interesting, and also quite different from financial reporting, which is the other application which seems to be taking off.
Category: Uncategorized
Hallucination in Neural NLG
Many neural NLG systems “hallucinate” non-existent or incorrect content. This is a major problem, since such hallucination is unacceptable in many (most?) NLG use cases. Also BLEU and related metrics do not detect hallucination well, so researchers who rely on such metrics may be misled about the quality of their system.
Where is NLG Most Successful Commercially?
From a commercial perspective, I think NLG is currently most successful in financial reporting. Although of course there are many great NLG applications in other sectors!
Varying Words In NLG Texts
Some thoughts on how to vary words in NLG text. This is aimed at practioners who are building NLG systems, not researchers.
Engineering Perspective: Understand Issues, Find Simple Solution
An approach I often take to NLG and indeed AI is to try to understand underying linguistic, NLG, and AI issues, and then to look for simple solutions to these issues.
Language Grounding and Context
Some thoughts on language grounding, especially choosing words to express data, and how this depends on context.
Use Proper Baselines!
Unfortunately I suspect many researchers make their results looks better by using poor baselines. I give some thoughts on this, based on a recent discussion with a PhD student.
Why I do not Want to be a Co-author on Your Paper
Some thoughts about when I feel comfortable being a coauthor on a paper, expressed as a letter to someone who put me on a paper as a co-author without asking me frst,
How Would I Automatically Evaluate NLG Systems?
Some musings on principled and theoretically sound techniques for automatically evaluating NLG systems.
How to Validate Metrics
My advice on how to perform a high-quality validation study, which assesses whether a metric (such as BLEU) correlates well with human evaluations.
Ehud Reiter's Blog 