When A.I. Falls in Love

https://www.youtube.com/watch?v=8qkCJeC-mco
Read More

#nlp, #videos

Remote Works

We’re going through a major transformation in the way we work. The workforce is moving out of the office in never before seen numbers. The pace has been dizzying and most of us are still trying to figure out how it’s done. Remote Works is a show to help you understand and embrace this rapid evolution. We’ll dig deep to find out how companies can securely and successfully move to remote work en masse. We’ll look at the mindset that’s required for high-performing distributed teams. You’ll meet people whose work depends on the tightest of connections and most dependable of tech. Experts share their insight on what the lasting changes will be to the places we work and what we need to adjust, stay productive and thrive. Read More

#podcasts

TLDR: Extreme Summarization of Scientific Documents

We introduce TLDR generation, a new form of extreme summarization, for scientific papers. TLDR generation involves high source compression and requires expert background knowledge and understanding of complex domain-specific language. To facilitate study on this task, we introduce SCITLDR, a new multi-target dataset of 5.4K TLDRs over 3.2K papers. SCITLDR contains both author-written and expert-derived TLDRs, where the latter are collected using a novel annotation protocol that produces high-quality summaries while minimizing annotation burden. We propose CATTS, a simple yet effective learning strategy for generating TLDRs that exploits titles as an auxiliary training signal. CATTS improves upon strong baselines under both automated metrics and human evaluations. Data and code are publicly available at https://github.com/allenai/scitldr. Read More

#nlp