FoG: The Birth of Commercial NLG
I did my Ph.D. on NLG in the late 1980s, 35 years ago! Amy Tobin, who runs the Arria blog, asked me to reflect on the early days of NLG. I […]
This 22-Year-Old Book on NLG is Still Relevant
Back in 2000, I wrote a book on Building Natural Language Generation Systems (co-authored with Robert Dale, who worked for Arria in its early years). Many people, including Arria staff
Humans Post-Editing NLG-Generated Narratives
There are times people want to edit an NLG-produced narrative before it is released; this is called “post-editing.” Typically, this involves adding additional content that is hard to automatically generate,
The Grand Challenge for NLG: Making Data Accessible to Humans
Twenty years ago, the UK Computing Research Committee asked me what my vision and “grand challenge” was for artificial intelligence (AI) and natural language generation (NLG). I told them that
Why Neural Language Models Don’t Work Well in NLG
I am often asked about neural language models such as BERT and GTP3, and whether Arria uses such models to generate text. I usually explain that while neural models have
NLG Drives Consistent Narratives
One of the advantages of using NLG to automate the production of narratives is that the language is consistent. When people write narratives, they write them in different ways depending
Finding Creative Solutions to Detect Mistakes in Neural-NLG Narratives
There is a lot of excitement in the NLG world about using neural (deep-learning) techniques to build NLG systems. However, one big problem with current neural NLG systems is that
The Power of Words
Words can be incredibly powerful when it comes to describing data. I remember once years ago when I was talking to an Arria client who wanted to summarize sensor-based alarms.
Chatbots Are a Great Way to Present Insights!
I am very excited about the potential of using chatbots to explain data to people. So far, chatbots have mostly been used for simple transactions like ordering pizzas, but they