PinnedMoshe WasserblatinTowards Data ScienceSentence Transformer Fine-Tuning (SetFit): Outperforms GPT-3 on few-shot Text-Classification while…The GPT-n series show very promising results for few-shot NLP classification tasks and keep improving as their model size increases [YK1]…15 min read·Dec 14, 2021--7--7
Moshe WasserblatZero-cost, ≈Zero inference-time, Zero-shot Financial Sentiment AnalysisHugging Face’s Moritz Laurer demonstrated in a great blog how to utilize pseudo-labeling data to achieve GPT-4 like performance with…5 min read·Mar 24, 2024----
Moshe WasserblatSetFitABSA (100M) outperforms Bloomberg (50B) on FiQA SABloombergGPT5 min read·Jan 14, 2024----
Moshe WasserblatEfficient Text Classification with Intel Neural CompressorIntel Neural Compressor is an open-source Python library for model compression that reduces the model size and increases the speed of deep…4 min read·Sep 23, 2022----
Moshe WasserblatBest Practices for Text Classification with Distillation (Part 1/4) — How to achieve BERT results…6 min read·May 18, 2021----
Moshe WasserblatFuture Directions for NLP in Commercial Environments — Intel AI LabNatural Language Processing (NLP) has made a major leap in the past decade, both in theory and in practical integration into broadly…7 min read·Mar 28, 2019----