Top all-time · #3674
natural language processing blog
Personal blog · nlpers.blogspot.comaidata
natural language processing blog is a personal blog at nlpers.blogspot.com about ai and data. Since 2009, 20 different Hacker News readers have linked it 22 times, most often “Debugging machine learning”. The last post was in 2018, but the archive is still widely read.
Too few sampled comments (5) to say how often HN recommends it.?
Why HN links it
HN readers link this NLP research blog for commentary on academic practice, such as reproducibility and supplementary materials, and for NLP topics like corpora and baselines.
Summarised by Claude from a sample of 5 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.)
Most-linked posts?
- Debugging machine learning2 people · 3 mentions · first linked 2016-08-24
- Google 5gram corpus has unreasonable 5grams2 people · 2 mentions · first linked 2010-06-16
- Food for thought for all researchers around2 people · 2 mentions · first linked 2016-12-12
What Hacker News says?
> "... it's a shame he'll likely need to get tenure before finishing it." Judging by his homepage [1] he is at least on the tenure track. Unless the notion of an Assistant Professor is different over in the states. I agree about the sentiment about the book, at least the chapter on Neural Networks needs some serious work (I believe there are errors in there, maybe I should mail Hal). As a person and researcher I onl…
Comment linking /
on “A Course in Machine Learning”Submitted Whence your reward function? as a story · 35 points
HN discussionBasically the same [1,2]. [1]: https://twitter.com/yoavgo/status/751178795323908096 [2]: https://nlpers.blogspot.com/2016/08/fast-easy-baseline-text-...
Comment linking /2016/08/fast-easy-baseline-text-categorization.html
on “How we built Tagger News: machine learning on a tight schedule”Submitted Machine Learning is the new Algorithms as a story · 25 points
HN discussionGood analysis of providing source code, datasets and potential burdens on reviewers and authors. http://nlpers.blogspot.com/2011/03/some-thoughts-on-suppleme...
Comment linking /2011/03/some-thoughts-on-supplementary.html
on “The Need for Reproducibility in Academic Research”Submitted Google 5gram corpus has unreasonable 5grams as a story · 25 points
HN discussionA popular nlp blogger posted ( http://nlpers.blogspot.com/2010/08/readers-kill-blogs.html ) about a related problem with comments (ie, that they're getting more and more distributed).
Comment linking /2010/08/readers-kill-blogs.html
on “Proposal: A new kind of blog comment system”Submitted Fast and easy baseline text categorization with Vowpal Wabbit as a story · 5 points
HN discussionGoogle released a trillion-word corpus with frequency counts for all sequences up to five words long... contains...all sorts of other errors...But the fact that it's a million times larger than the Brown Corpus outweighs these drawbacks. Maybe not: http://nlpers.blogspot.com/2010/02/google-5gram-corpus-has-u...
Comment linking /2010/02/google-5gram-corpus-has-unreasonable.html
on “The unreasonable effectiveness of data”Submitted Many opportunities for discrimination in deploying machine learning systems as a story · 3 points
HN discussionSubmitted Machine learning is the new algorithms as a story · 3 points
HN discussionSubmitted Food for thought for all researchers around as a story · 2 points
HN discussionSubmitted Should the NLP and ML Communities Have a Code of Ethics? as a story · 2 points
HN discussionSubmitted Debugging machine learning as a story · 2 points
HN discussionSubmitted Language Bias and Black Sheep as a story · 2 points
HN discussionSubmitted A technique for me is a task for you as a story · 2 points
HN discussionSubmitted Debugging machine learning as a story · 1 points
HN discussionSubmitted Debugging machine learning as a story · 1 points
HN discussionSubmitted Why “strong” is not a total order for NLP baselines as a story · 1 points
HN discussionSubmitted My NAACL 2013 list... as a story · 1 points
HN discussionSubmitted Comparing Bounds as a story · 1 points
HN discussionSubmitted Recommended NLP, ML, and CL papers as a story · 1 points
HN discussion
