#NLProc

Ok, one probably-last call for teaching ideas/resources bc #NLProc twitter has so many of themTomorrow I'm teaching about ethics of NLP for COVID (I surveyed my students, this was the

Going on with the #NLProc peer review debate!The most thorny issue so far: should *ACL should require resource papers to have some proof-of-concept application?* FOR: no ML experiments => go

Almost every article on Scots Wikipedia is written by one American teenager, who does not speak Scots and is just writing English in an "accent".If you have a multilingual language

There is a lot I like about this book. It's well-written, and includes a lot on the scientific study of groups (i.e. it's not a business book containing some CEO's

Recently came across a quick read from @laroyo & @cawelty (2015) in AI Magazine on 7 "myths" about data collection. Their perspective is still worth thinking about b/c...1/10 -Many of

Christoph Purschke

The fun of working with low-resource languages... First working prototype of an automatic orthographic correction tool for #Luxembourgish in #Python. Still a bit resource-heavy, and it needs better correction dicts

As pretrained language models grow more common in #NLProc, it is crucial to evaluate their societal biases. We launch a new task, evaluation metrics, and a large dataset to measure

Emiel van Miltenburg

Some notes regarding inter-annotator agreement in NLG:Krippendorff (2004; https://repository.upenn.edu/cgi/viewcontent.cgi?article=1250&context=asc_papers) compares different measures for inter-annotator agreement and shows (following earlier lit

Tweet thread recording joyful moments as I'm reading @tteofili https://www.manning.com/books/deep-learning-for-search#nlproc #neuralengine #neuralempty Section 1.9 "Index, please meet neuron" is really enlightening, esp. the b

Shyam Sunder Kumar

shyam_sunder_kr

Thankyou for starting #25DaysOfNLP @abhi1thakur .Here are few things that would be nice if covered to some extent . Would love to contribute as well. Please fell free to add

Language model prompting is all the rage lately in #NLProcLet me break down what it is, why researchers are studying it, and how it enables surprising zero/few-shot performance across a

Dave 🦔 hopes you are at home 💛

Here's the thing with #260papers: some days you read more, some days you read less, but averaging a paper per work day seems like a lot, especially since that expects