Come join the 4 of us and answer exciting research questions!
I’m looking for PhD students who want to: 1) understand the role of input in shaping generalization behavior — how do different sources of positive and negative evidence conspire together to give rise to learning?…
Chandrayaan-3 Mission:
'India🇮🇳,
I reached my destination
and you too!'
: Chandrayaan-3
Chandrayaan-3 has successfully
soft-landed on the moon 🌖!.
Congratulations, India🇮🇳!
#Chandrayaan_3#Ch3
Our paper on analyzing language modeling acceptability judgments with systematically manipulated contexts was recognized as an outstanding paper—thanks so much to the reviewers and the best paper award committee!
New paper to be presented on Saturday (July 30) at #CogSci2022@cogsci_soc
We (@AllysonEttinger, Julia Rayz, and I) present a paradigm to perform property induction using LLMs!
paper: https://t.co/CHJfcWLsqc
(WARNING: long thread 😬)
Do pre-trained LM predictions reflect "understanding" of the meanings of input contexts? Or mostly shallower heuristics? Come chat with @LalchandPandia and me about how we teased these apart - tomorrow's virtual interpretability poster session #EMNLP2021 (https://t.co/N2tyTKvgap)
University of British Columbia is excited to have hired @VeredShwartz to Computer Science, who brings her expertise in #NaturalLanguageProcessing
Read: https://t.co/c8tGe8pO88
A second paper from @LalchandPandia, also with @stellacong1: we find that pre-trained LMs are very weak at picking up on pragmatic cues relating to discourse connectives https://t.co/yEwvL6eCXY (to be presented at CoNLL).
Delayed tweet, I know, but I'm excited to share @LalchandPandia's EMNLP paper https://t.co/N2tyTKdFiR! We test information processing in pre-trained LMs by providing meaning information relevant for prediction, and pitting it against irrelevant attractors in context. 1/3
When generating research ideas, having bad ideas is unavoidable. The important thing to remember is that:
*having bad ideas* does not mean *you are bad at generating ideas*
Most good ideas are the product of lots of bad ideas, and finding the good ones is a skill you can build.
@evanmiltenburg@windx0303@jeffbigham In the Author response page, there is a hyperlink HERE in the instructions section. Once you click on it, you will be taken to a new page and look at the Overall Tecommendation section. It lists the score definitions