Notes from a Dev Conf: Sensible Attitude to Trendy AI Tech, Arria Presentations
I went to my first developers conference last week and was impressed, not least by the sensible attitude towards deep learning and other trendy AI technology.
Use Good Engineering Methodology When Building NLG Systems!
Good software engineering is criticial when building NLG systems, including requirements analysis, design, testing, and support.
Please Use Two-Tailed P Values!
If you are writing a scientific paper which presents statistics, please use two-tailed p values unless you **really** know what you are doing.
How do I Learn about NLG?
Some suggestions for people who are new to NLG and want to learn more about it.
Dealing with Edge Cases in NLG
I give some high-level advice on handling edge cases in NLG. As with any software system, most of the effort in building NLG systems usually goes into handling edge cases.
Goodbye to a Synagogue
I was very sad to hear that the Jewish synagogue in the Scottish town of Dundee is likely to close
Should I Use Deep Learning?
There is a lot of hype around deep learning. especially at business-oriented AI events. I suggest some questions to think about for companies who are considering using DL.
My Guidelines for Evaluating AI Systems
Ehud’s guidelines for evaluating AI systems: keep it simple, keep it ethical, be careful, do proper stats, and be skeptical
Managing Research Projects is Painful but Necessary
Managing research projects is not much fun, but it is important. I have seen many research projects which did not reach their potential or even failed completely, because of poor management.
Testing Multiple Hypotheses
The NLP/AI community needs to do a better job of dealing with multiple hypotheses, otherwise a lot of our results will be garbage.
Ehud Reiter's Blog 