Published inTowards Data ScienceSemantic Signal SeparationUnderstand Semantic Structures with Transformers and Topic ModelingFeb 112Feb 112
Published inTowards Data ScienceExplore Semantic Relations in Corpora with Embedding ModelsRecently I have talked to a handful of fellow students and scholars who had research interests which involved the analysis of free-form…Nov 24, 20232Nov 24, 20232
Finetuning Static Word Embedding ModelsImprove accuracy on downstream tasks for absolutely no hit in performance with a simple trick and the power of JAX.Sep 12, 2023Sep 12, 2023
Zero and Few-Shot Classification with Transformers, LLMs and stormtrooperIntegrate zero and few-shot classification seamlessly into your scikit-learn workflows.Aug 19, 2023Aug 19, 2023
Unsupervised Text Classification with Topic Models and Good Old Human ReasoningUse your brain and your data interpretation skills, and create production-ready pipelines without labeled dataAug 3, 20232Aug 3, 20232
Blazing Fast Fuzzy Search in Python with NeofuzzNeofuzz (https://x-tabdeveloping.github.io/neofuzz/) is a fuzzy or semantic string matching library for Python, that I developed, because…May 26, 2023May 26, 2023
Topic modelling over short texts with tweetopicA fast, scalable and high-quality approach to modelling short texts and Tweets.Feb 23, 2023Feb 23, 2023
Visualizing topic models with topicwizardInvestigate your topic models interactively with beautiful and powerful visualizations.Feb 19, 20236Feb 19, 20236