Most reviewing is a chore, but reviewing for TACL is fun. I learn things and feel I “add value”, which is much rarer in conference reviewing. Plus I can focus on one paper at a time, since TACL reviewing is spread out across the year.
If an NLG system produces inferior texts once in a while, should we ask a human writer to “post-edit” NLG texts? I review some of the literature and give some advice.
The Tibco Covid dashboard is a nice example of how NLG narratives can “add value” to complex visualisations. Hopefully we’ll see more dashboards like this!
A colleague asked me if it was true that building neural NLG systems was faster than building rule-based NLG systems. The answer is that we dont know, because we dont have good data on this question. However the weak evidence we do have suggests that building rules-based NLG is no slower and may be faster than building neural NLG, at least for data-to-text systems.
Accuracy errors in NLG texts go far beyond simple factual mistakes, for example they also include misleading use of words and incorrect context/discourse inferences. All of these types of errors are unacceptable in most data-to-text NLG use cases.
The Covid crisis gives us a chance to rethink and change our conference culture. I would like to see fewer large international conferences, and also have these focus on discussion and interaction rather than on oral presentations.
A PhD student recently complained that to me that he was wasting a lot of time reading scientifically dubious papers. I give some suggestions on indicators of poor scientific quality in research papers.
I’d love to see more people using machine learning to provide insights about NLG problems and related linguistic issues. I personally think this is much more useful than tweaking models to show a 1% increase in state-of-art in a very artificial context.
NLP technology has changed and advanced over the past two decades, but it often seems that NLG evaluation has not. Why is the 18-year old BLEU metric still so dominant?
We’re thinking of organising a shared task on evaluating the accuracy of texts produced by NLG systems. Comments welcome, also let me know if you might participate.