Talking to GPT-2
GPT-2 is yet another in a succession of models like ELMo and BERT which adopt a similar deep learning architecture and train an unsupervised model on a massive text corpus. As we have been covering re...
31 Okt 201929min
Reproducing Deep Learning Models
Rajiv Shah attempted to reproduce an earthquake-predicting deep learning model. His results exposed some issues with the model. Kyle and Rajiv discuss the original paper and Rajiv's analysis.
23 Okt 201922min
What BERT is Not
Allyson Ettinger joins us to discuss her work in computational linguistics, specifically in exploring some of the ways in which the popular natural language processing approach BERT has limitations.
14 Okt 201927min
SpanBERT
Omer Levy joins us to discuss "SpanBERT: Improving Pre-training by Representing and Predicting Spans". https://arxiv.org/abs/1907.10529
8 Okt 201924min
BERT is Shallow
Tim Niven joins us this week to discuss his work exploring the limits of what BERT can do on certain natural language tasks such as adversarial attacks, compositional learning, and systematic learning...
23 Sep 201920min
BERT is Magic
Kyle pontificates on how impressed he is with BERT.
16 Sep 201918min
Applied Data Science in Industry
Kyle sits down with Jen Stirrup to inquire about her experiences helping companies deploy data science solutions in a variety of different settings.
6 Sep 201921min
Building the howto100m Video Corpus
Video annotation is an expensive and time-consuming process. As a consequence, the available video datasets are useful but small. The availability of machine transcribed explainer videos offers a uniq...
19 Aug 201922min
