Discover and read the best of Twitter Threads about #acl2017nlp
Most recents (5)
ACL business meeting: Chris Manning talking now (I missed what looked like a good anti-arxiv position) #acl2017nlp
equity is essential; double-blind is best way to preserve it
despite this, can't support banning arxiv---fast turnaround has been major boon to DL community
Luheng He on deep SRL: homes.cs.washington.edu/~luheng/files/… #acl2017nlp
previous SOTA is a CRF with neural potentials; here we're just going to train greedily (?) and Viterbi decode at test
NN is not smart enough to learn what well-formed BIO taggings look like, so add hard constraints
Next: Tim Vieira on learning to prune #acl2017nlp
we're going to learn to prune a coarse-to-fine DP by optimizing a linear combination of accuracy & runtime
in constituency parsing, runtime is a function of the number of chart cells we explore
Next: Ravi Shekhar on breaking captioning models arxiv.org/abs/1705.01359 #acl2017nlp
Take a captioned image, replace one noun with a different noun that makes it a false caption. Can do this automatically w/ COCO cat labels
Tasks: classify captions, detect the impostor word, correct it
Next: Omri Abend with a survey of the (huge) number of new semantic annotation schemes proposed in recent years #acl2017nlp
I wish there were better incentives for people to write survey papers
main difference between "syn" and "sem" is respect for *distributional* behavior
