NLP News By Sebastian Ruder Regular analyses of advances in natural language processing and machine learning. 62 issues Subscribe to our newsletter By subscribing, you agree with Revue’s Terms of Service and Privacy Policy and understand that NLP News will receive your email address.
Pre-training + Massive Multi-tasking, Benchmarking in NLP, EMNLP primer, 🤗 NLP Course, ACL 2021 recap, #62 Nov 6, 2021
ICML round-up, Open collaboration, CLIP art, Internet augmentation, New GLUE-style benchmarks #61 Aug 2, 2021
GitHub Copilot, The Perceiver, Beyond the Transformer, Data augmentation, NL augmenter 🦎 → 🐍, Research communication #60 Jul 19, 2021
#59 May 4, 2021 EACL, ICLR, NAACL papers round-up, Research reality checks, ML on code – Hi there,I've spent the last days catching up on papers—before inevitably falling behind again once A
#58 Apr 6, 2021 ICLR 2021 Outstanding Papers, Char Wars, Speech-first NLP, Virtual conference ideas – Hi there,I hope you've had the chance to take some time off and relax recently. Here in the UK, thing
#57 Mar 23, 2021 QA—how did we get here? 🙋♀️, Adapting to time ⏳, Data detectives 🕵️♀️ – Hi all,A struggle for me these days is the lack of human connection and interaction. I think this is
#56 Feb 15, 2021 IE—how did we get here?, Large LMs, The human side of ML – Hi all,I hope you've had a good start to the new year. This newsletter is a bit delayed due to a conf
#55 Dec 23, 2020 EMNLP 2020 recap, Minimum viable datasets, Efficiency, Roguelikes for RL Research – Hi all,I sincerely hope that this year was an extreme outlier and that 2021 will be again more in-dis
#54 Nov 13, 2020 EMNLP 2020 & ICLR 2021, Toxicity detection, Data augmentation and adversarial examples – Hi all,With EMNLP 2020 coming up next week and ICLR 2021 reviews just out, this newsletter contains a
#53 Oct 13, 2020 ML and NLP starter toolkit, Low-resource NLP toolkit, "Can a LM understand natural language?", The next generation of NLP benchmarks – Hi all,It has been a while... I hope you're doing well in these crazy and strange times.COVID-19 has
#52 Jun 5, 2020 Reviewing, Taking stock, Theme papers, Poisoning and stealing models, Multimodal generation – Hi all,This newsletter took somewhat longer than usual. This is both due to lower energy ⚡️on my side
#51 Apr 15, 2020 COVID-19 edition 😷 – Hi all,I hope you're all staying safe in these trying times. 🤒 This is a shorter version of the usual
#50 Mar 27, 2020 COVID-19, Hutter Prize, Compression = AGI?, BERT, Green AI – Hi all,This newsletter is a bit delayed due to some adjustments in light of the ongoing coronavirus p
#49 Feb 25, 2020 Accelerating science, memorizing vs learning to look things up, Schmidhuber's 2010s, Greek BERT, ARC, Illustrated Reformer, Annotated GPT-2, oLMpics – Hi all,This newsletter discusses accelerating science, memorizing vs learning to look things up, and
#48 Jan 27, 2020 NLP Progress, Restrospectives and look ahead, New NLP courses, Independent research initiatives, Interviews, Lots of resources – Happy 2020 everyone 🎉! May your models be sample-efficient, your generalisation error be low, and you
#47 Dec 23, 2019 2020 NLP wish lists, HuggingFace + fastai, NeurIPS 2019, GPT-2 things, Machine Learning Interviews – Happy holidays everyone! 🕯🎄🕎I hope you all had a fantastic year. The last newsletter of 2019 conclude
#46 Nov 19, 2019 Highlights of EMNLP 2019, Ethics in NLP vol. 2, AI and Journalism – Hi all,The themes of this newsletter are highlights from EMNLP 2019, ethical uses of NLP, and AI and
#45 Oct 22, 2019 Deep Learning Indaba, EurNLP, ML echo chamber, Pretrained LMs, Reproducibility papers – Hi all,This month features updates about recent events (ICLR 2020 submissions, Deep Learning Indaba,
#44 Sep 16, 2019 Experimental results and error reporting, Ethics and NLP, Distillation vol. 2, SemEval 2020 – Hi all,This edition is about better ways to report experimental results and model errors, ethics and
#43 Aug 21, 2019 Bigger vs. smaller models, powerful vs. dumb models – Hi all,The theme of this newsletter are juxtapositions: training ever bigger models (GPT-8 8B) vs. ma
