Daulet NurmanbetovinTowards Data ScienceBERT Model Embeddings aren’t as good as you thinkToward multilingual sentence embeddingsMay 31, 20201May 31, 20201
Daulet NurmanbetovinTowards Data ScienceSQL-like window functions in PandasA Single Place for all Pandas Window FunctionsMay 14, 20202May 14, 20202
Daulet NurmanbetovinTowards Data ScienceCutting edge semantic search and sentence similaritySemantic search is a hard problem worth solving in NLP.May 4, 20202May 4, 20202
Daulet NurmanbetovinTowards Data ScienceSummarization has gotten commoditized thanks to BERTState of the art Summarization available for anyoneMar 12, 20201Mar 12, 20201
Daulet NurmanbetovinTowards Data ScienceCrowd-Sourced Data LabelingHow to increase the robustness of crowd-labelersMar 12, 2020Mar 12, 2020
Daulet NurmanbetovinTowards Data ScienceBootstrapping cutting-edge NLP modelsHow to get up and running with XLNet and Pytorch in 5 minsFeb 20, 2020Feb 20, 2020
Daulet NurmanbetovinThe StartupWeak Supervision, Future of Data LabelingOverview of data labeling for AI, new paradigms, and size of the growing data labeling market.Feb 9, 20201Feb 9, 20201
Daulet NurmanbetovinTowards Data ScienceExtracting Data from Financial PDFsHow to quickly extract text and data from Municipal Bond CAFR ReportsNov 23, 20194Nov 23, 20194
Daulet NurmanbetovinTowards Data ScienceGuide on AWS Textract set-upOn how to accurately process PDF files with OCR-as-a-serviceNov 2, 20192Nov 2, 20192
Daulet NurmanbetovinTowards Data ScienceMultilingual Sentence Models in NLPOverview of two major multilingual sentence embedding modelsOct 22, 20193Oct 22, 20193