I am super reticent to write this because so many people have written similar things. Yet despite that, we still have things like an initial workshop program with 17 invited speakers of whom 16 a...
https://nlpers.blogspot.com/2018/07/yet-another-list-of-things-we-can-do-to.html
A while ago I created this image for thinking about how machine learning systems tend to get deployed. In this figure, for Chapter 2 of CIML , the left column shows a generic decision being ...
https://nlpers.blogspot.com/2018/06/many-opportunities-for-discimination-in.html
Score-based multiclass classifiers typically have the following form: x is a d-dimensional input vector (perhaps engineered features, perhaps learned features), A is a d*k matrix, where k is the ...
https://nlpers.blogspot.com/2017/08/column-squishing-for-multiclass-updates.html
Like lots of folks, I wonder sometimes about AI and jobs. I'm neither a believer that there's a catastrophe coming up, nor am I a believer that everything will magically work out and we're not en...
https://nlpers.blogspot.com/2017/04/humans-can-still-extort-more-money-from.html
It's really strange to look back now over the past ten to fifteen years and see a very small pendulum that no one really cares about swing around. I've spent the last ten years trying to convinc...
https://nlpers.blogspot.com/2017/04/structured-prediction-is-not-rl.html
There are a handful of definitions of "fairness" lying around, of which the most common is disparate impact: the rate at which you hire members of a protected category should be at least 80% of t...
https://nlpers.blogspot.com/2017/03/initial-thoughts-on-fairness-in-paper.html
Over the past week, in honor women of this International Women's Day , I had a several posts, broadly around the topic of women in STEM. Previous posts in this series include: Awesome People: Bon...
https://nlpers.blogspot.com/2017/03/trying-to-learn-how-to-be-helpful-iwd.html
To honor women this International Women's Day , I have a several posts, broadly around the topic of women in STEM. Previous posts in this series include: Awesome People: Bonnie Dorr , Awesome Peo...
https://nlpers.blogspot.com/2017/03/awesome-people-kathy-mckeown-iwd.html
To honor women this International Women's Day , I have a several posts, broadly around the topic of women in STEM. Previous posts in this series include: Awesome People: Bonnie Dorr , Awesome Peo...
https://nlpers.blogspot.com/2017/03/awesome-women-karen-sparck-jones-iwd.html
To honor women this International Women's Day , I have a several posts, broadly around the topic of women in STEM. Previous posts in this series include: Awesome People: Bonnie Dorr and Awesome ...
https://nlpers.blogspot.com/2017/03/awesome-people-lise-getoor-iwd.html
To honor women this International Women's Day , I have a several posts, broadly around the topic of women in STEM. Previous posts in this series include: Awesome People: Bonnie Dorr . Today is ...
https://nlpers.blogspot.com/2017/03/awesome-people-ellen-riloff-iwd.html
To honor women this International Women's Day , I have a several posts, broadly around the topic of women in STEM. This is the first, and the topic is "who has been influential in my career and...
https://nlpers.blogspot.com/2017/03/awesome-people-bonnie-dorr-iwd.html
At ACL this past summer, Dirk Hovy and Shannon Spruit presented a very nice opinion paper on Ethics in NLP. There's also been a great surge of interest in FAT-everything (FAT = Fairness, Accounta...
https://nlpers.blogspot.com/2016/12/should-nlp-and-ml-communities-have-code.html
I ran a grad seminar in reinforcement learning this past semester , which was a lot of fun and also gave me an opportunity to catch up on some stuff I'd been meaning to learn but haven't had a ch...
https://nlpers.blogspot.com/2016/12/whence-your-reward-function.html
I've attended and organized two types of workshops in my time, one of which I'll call the ACL-style workshop (or "mini-conference"), the other of which I'll call the NIPS-style workshop (or "actu...
https://nlpers.blogspot.com/2016/11/workshops-and-mini-conferences.html
Yesterday I gave a super duper high level 12 minutes presentation about some issues of bias in AI. I should emphasize (if it's not clear) that this is something I am not an expert in; most of wha...
https://nlpers.blogspot.com/2016/11/bias-in-ml-and-teaching-ai.html
In case you missed it, Regina Barzilay and Min-Yen Kan, who are program chairs for ACL 2017, are running an open blog describing what they're doing: https://chairs-blog.acl2017.org/ Check ...
https://nlpers.blogspot.com/2016/11/acl-2017-pc-chairs-blog.html
I've been thinking, mostly in the context of teaching, about how to specifically teach debugging of machine learning. Personally I find it very helpful to break things down in terms of the usual ...
https://nlpers.blogspot.com/2016/08/debugging-machine-learning.html
I wrote my first (and only) coreference paper back in 2005. At the time, my goals were to (a) do well on coref, (b) integrate background knowledge (like "Bush" is "president") using simple techn...
https://nlpers.blogspot.com/2016/08/feature-or-architecture-ablation.html
A conference just ended, so it's that time of year! Here are some papers I liked with the usual caveats about recall. Before I go to the list, let me say that I really really enjoyed ACL this y...
https://nlpers.blogspot.com/2016/08/some-papers-i-liked-at-acl-2016.html
About a month ago, the paper Bag of Tricks for Efficient Text Categorization was posted to arxiv. I found it thanks to Yoav Goldberg's rather incisive tweet : Yoav is basically referring to t...
https://nlpers.blogspot.com/2016/08/fast-easy-baseline-text-categorization.html
When I think of structured input models, I typically think of things like kernels over discrete input spaces. For instance, the famous all-substrings kernel for which K(d1,d2) effectively counts...
https://nlpers.blogspot.com/2016/07/a-quick-comment-on-structured-input-vs.html
I remember back in grad school days some subset of the field was thinking about the following question. I train an unsupervised HMM on some language data to get something-like-part-of-speech tags...
https://nlpers.blogspot.com/2016/07/decoding-neural-representations.html
Usual caveats: didn't see all talks, didn't read all papers, there's lot of good stuff at NAACL that isn't listed here! That said, here are some papers I particularly liked at NAACL, with some c...
https://nlpers.blogspot.com/2016/07/some-picks-from-naacl-2016.html
Groan groan groan reviewers are horrible people. Not you and me. Those other reviewers over there! TLDR: In general we actually don't think our reviews are that bad, though of course it's easy t...
https://nlpers.blogspot.com/2016/07/rating-quality-of-reviews-after-fact.html