my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) I feel a bit odd doing my "what I liked at NAACL 2013" as one of the program chairs, but not odd enough to skip what seems to be the most popular type of post :). First, though, since Katrin Kirchhoff (my co-chair) and I never got a chance

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) I'm using ACL/ICML as an excuse to jumpstart my resumed, hopefully regular, posting.  The usual "I didn't see/read everything" applies to all of this.  My general feeling about ACL (which was echoed by several other participants) was that

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) I try to be a good reviewer, but like everything, reviewing is a learning process.  About five years ago, I was reviewing a journal paper and made an error.  I don't want to give up anonymity in this post, so I'm going to be vague in place

timv said... I've definitely felt the IO bottleneck before.. the best solution is to get a really beefy 64-bit multi-core machine with tons of memory to run all your training on. This way you can leave everything in memory.. no more worries! Have you considered posing this as a question on MetaOptimize (http://metaoptimize.com/qa)? 31 August, 2010 22:24 John Langford said... I've seen VW work pret

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) ACL 2010 finished up in Sweden a week ago or so. Overall, I enjoyed my time there (the local organization was great, though I think we got hit with unexpected heat, so those of us who didn't feel like booking a room at the Best Western --

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) Just got back from Israel for ICML, which was a great experience: I'd wanted to go there for a while and this was a perfect opportunity. I'm very glad I spent some time afterwards out of Haifa, though. Overall, I saw a lot of really good s

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) I just returned from NAACL 2010, which was simultaneously located in my home town of Los Angeles and located nowhere near my home town of Los Angeles. (That's me trying to deride downtown LA as being nothing like real LA.) Overall I was pl

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) In the context of something completely unrelated, I was looking for a fairly general pattern in the Google 1TB corpus. In particular, I was looking for verbs that are sort of transitive. I did a quick grep for 5grams of the form "the SOMET

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) This isn't so much a post in the "GSI" series, but just two links that recently came out. Kevin Knight and Philip Resnik both just came out with tutorials for Bayesian NLP. They're both excellent, and almost entirely non-redundant. I highl

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) Well, ACL and EMNLP are long gone. And sadly I missed one day of each due either to travel or illness, so most of my comments are limited to Mon/Tue/Fri. C'est la vie. At any rate, here are the papers I saw or read that I really liked. P09

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) There is a cool view of the whole non-parametric Bayes thing that I think is very instructive. It's easiest to see in the case of the Pitman-Yor language modeling work by Frank Wood and Yee Whye Teh. The view is "memorize what you can, and

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) If you compare vision research with NLP research, there are a lot of interesting parallels. Like we both like linear models. And conditional random fields. And our problems are a lot harder than binary classification. And there are standar

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) This will probably be a bit briefer than my corresponding NAACL post because even by day two of ICML, I was a bit burnt out; I was also constantly swapping in other tasks (grants, etc.). Note that John has already posted his list of papers

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) (Guest post by Kevin Duh. Thanks, Kevin!) At the NAACL SSL-NLP Workshop recently, we discussed whether there ought to be a "shared task" for semi-supervised learning in NLP. The panel discussion consisted of Hal Daume, David McClosky, and

my biased thoughts on the fields of natural language processing (NLP), computational linguistics (CL) and related topics (machine learning, math, funding, etc.) Those who talk to me a lot over the years know that I really think that generation is a cool and interesting problem, but one that is hampered by a lack of clarity of what it is, or at least what the input/output is. It's like the problem