NLP à la Suisse

on YouTube ↗45m

" summary

An overview of modern Natural Language Processing components and how they fit into a pipeline, covering tokenization, lemmatization, named entity recognition, coreference resolution, and dependency parsing. It also explains where large language models such as GPT can be integrated to enhance processing. The techniques are demonstrated on the multilingual Swiss Commercial Registry dataset to show practical, Switzerland-specific challenges and applications.

AI-written summary · about

" chapters (10)

1. 0:00NLP in Swiss context
2. 2:56What is NLP
3. 8:16SpaCy pipeline basics
4. 15:41NER pipeline
5. 22:06Extracting origins and domiciles
6. 26:20Linking entities to data
7. 31:25Visualizing domicile and origin maps
8. 35:21LLMs for NER
9. 39:38Summary
10. 42:06Q&A

" related talks

• 06mAdvancements in Natural Language Processing (NLP) and Text AnalyticsNada GabAllah · DSC MENA 2024
• 31mNatural Language Processing & JavaDeepu Xavier · Eclipse Summit India 2017
• 55mDemystifying Natural Language Processing across several industry verticalsJyotika Singh · DjangoCon US 2021
• 30mBuilding Complete State of the art Natural Language ProcessingDavid Talby · Scale By the Bay 2021
• 23mMultilingual Natural Language ProcessingGajendra Deshpande · Conf42 Machine Learning 2021
• 17mNatural Language Processing in AutomationSweta Patra · DevConf.CZ 2023
• 26mNatural Language Processing (NLP) going mainstreamAlice Chung · Global Artificial Intelligence Virtual Conference 2022
• 20mPolyglot AI: The Role of Natural Language Processing (NLP)Rama Akkiraju · Women in Data Science (WiDS) Stanford 2020