Is GenAI All You Need to Classify Text? Some Learnings from the Trenches

🔊 Recorded at PyCon DE & PyData Berlin 2024, 24.04.2024 2024.pycon.de/program/CWUQF3/ 🎓 Watch how a small dedicated model outperforms GenAI in text classification efficiency and adaptability, presented by Marc Palyart and Kateryna Budzyak from Malt. Speakers: Marc Palyart, Kateryna Budzyak Description: The talk by Marc Palyart, Head of Data Science at Malt, and Kateryna Budzyak, Data Scientist at the same company, discussed the practical implications of using GenAI for text classification tasks. The speakers highlighted challenges such as latency, environmental impact, and budget constraints when employing GenAI. To address these issues, they developed a smaller, dedicated model based on a pre-trained SentenceBERT model, focusing on semantic similarity. They also emphasized the importance of training a classification network on top of it to preserve language alignment for multilingual generalization. Additionally, the speakers discussed optimization techniques like quantization and graph optimization through the ONNX ecosystem, enabling the deployment of the dedicated model with just a CPU. Despite these optimizations, they acknowledged GenAI's zero-shot capabilities, which allow for continuous adaptation of the dedicated model to maintain its relevance in evolving environments. ⭐️ About PyCon DE & PyData Berlin: The PyCon DE & PyData conference unite the Python, AI, and data science communities, offering a unique platform for collaboration and innovation. The PyCon DE & PyData Berlin 2024 conference, hosted in partnership with the local Berlin PyData chapter, provided an exceptional experience, fostering deeper connections within the Python community while showcasing advancements in AI and data science. Attendees enjoyed a diverse and engaging program, solidifying the event as a highlight for Python and AI enthusiasts nationwide. Follow us: • LinkedIn: www.linkedin.com/company/28908640/ • X: www.x.com/pyconde • X: www.x.com/pydataberlin Links: • Conference website: pycon.de/ • Related sessions: 2024.pycon.de/program/categories/pydata-natural-la… The conference is organized by • Python Softwareverband e.V.: pysv.org/ • NumFOCUS Inc.: numfocus.org/ • Pioneers Hub gemeinnützige GmbH: pioneershub.org/ If you enjoyed this session, please like, comment, and subscribe to our channel for more insightful talks and discussions. Share this video with your network to spread the knowledge! Hashtags: #Python #PyConDE #PyData #OpenSource #AI #DataScience #MachineLearning #SoftwareDevelopment #LLMs #Community Acknowledgements: Special thanks to all the volunteers and sponsors who made this event possible. About: Python Softwareverband e.V.: PySV is a non-profit that promotes the use and development of Python in Germany through events, education, and advocacy, fostering an open Python community. NumFOCUS Inc. supports open-source scientific computing by providing financial and logistical support to key projects like NumPy and Jupyter, promoting sustainable development and collaboration. Pioneers Hub gemeinnützige GmbH: is a non-profit fostering innovation in AI and tech by connecting experts and promoting knowledge exchange through events and collaborative initiatives. www.pydata.org PyData is an educational program of NumFOCUS, a 501(c)3 non-profit organization in the United States. PyData provides a forum for the international community of users and developers of data analysis tools to share ideas and learn from each other. The global PyData network promotes discussion of best practices, new approaches, and emerging technologies for data management, processing, analytics, and visualization. PyData communities approach data science using many languages, including (but not limited to) Python, Julia, and