Natural Language Processing & Audio (incl. Generative AI NLP)
15 talks from the 2025 edition.
-
Autonomous Browsing using Large Action Models ▶ Recording 📝 Transcript
Nico Kreiling, Arne Grobrügge
The browser serves as our gateway to the internet—the largest repository of knowledge in human history. Proficiency in its use is a core skill across nearly all professions and is becoming increasingly important for...
-
Beyond Basic Prompting: Supercharging Open Source LLMs with LMQL's Structured Generation ▶ Recording 📝 Transcript
Christiaan Swart
This intermediate-level talk demonstrates how to leverage Language Model Query Language (LMQL) for structured generation and tool usage with open-source models like Llama. You will learn how to build a RAG system...
-
Building a HybridRAG Document Question-Answering System ▶ Recording 📝 Transcript
Darya Petrashka
Retrieval Augmented Generation (RAG) is a powerful technique for searching across unstructured documents, but it often falls short when the task demands an understanding of intricate relationships between entities....
-
Building an Open Source RAG System for the United Nations Negotiations on Global Plastic Pollution ▶ Recording 📝 Transcript
Rahkakavee Baskaran, Teresa Kroesen, Anna-Lisa Wirth
Plastic pollution is a significant global challenge. Every year, millions of tons of plastic enter the oceans, impacting marine ecosystems and human health. To address this issue, the United Nations is negotiating a...
-
Building Reliable AI Agents for Publishing: A DSPy-Based Quality Assurance Framework ▶ Recording 📝 Transcript
Simonas Černiauskas
As publishers increasingly adopt AI agents for content generation and analysis, ensuring output quality and reliability becomes critical. This talk introduces a novel quality assurance framework built with DSPy that...
-
Code & Community: The Synergy of Community Building and Task Automation ▶ Recording 📝 Transcript
Cosima Meyer
The Python community is built on a culture of support, inclusion, and collaboration. Sustaining this welcoming environment requires intentional community-building efforts, which often involve repetitive or...
-
Conquering PDFs: document understanding beyond plain text ▶ Recording 📝 Transcript
Ines Montani
NLP and data science could be so easy if all of our data came as clean and plain text. But in practice, a lot of it is hidden away in PDFs, Word documents, scans and other formats that have been a nightmare to work...
-
Decoding Topics: A Comparative Analysis of Python’s Leading Topic Modeling Libraries Using Climate C ▶ Recording 📝 Transcript
Dr. Lisa Andreevna Chalaguine
Topic modelling has come a long way, evolving from traditional statistical methods to leveraging advanced embeddings and neural networks. Python’s diverse library ecosystem includes tools like Latent Dirichlet...
-
Electify - Retrieval-Augmented Generation for Voter Information in the 2024 European Election ▶ Recording 📝 Transcript
Christian Liedl
In general elections, voters often face the challenge of navigating complex political landscapes and extensive party manifestos. To address this, we developed Electify, an interactive application that utilizes...
-
Generative-AI: Usecase-Specific Evaluation of LLM-powered Applications ▶ Recording 📝 Transcript
Dr. Homa Ansari
This talk addresses the critical need for usecase-specific evaluation of Large Language Model (LLM)-powered applications, highlighting the limitations of generic evaluation benchmarks in capturing domain-specific...
-
Is Prompt Engineering Dead? How Auto-Optimization is Changing the Game ▶ Recording 📝 Transcript
Iryna Kondrashchenko, Oleh Kostromin
The rise of LLMs has elevated prompt engineering as a critical skill in the AI industry, but manual prompt tuning is often inefficient and model-specific. This talk explores various automatic prompt optimization...
-
Is your LLM any good at writing? Benchmarking on creative writing and editing tasks ▶ Recording 📝 Transcript
Azamat Omuraliev
Many LLM benchmarks focus on reasoning and coding tasks. These are exciting tasks! But the majority of LLM usage is still in writing and editing related tasks, and there's a surprising lack of benchmarks on these. In...
-
Modern NLP for Proactive Harmful Content Moderation ▶ Recording 📝 Transcript
Daryna Dementieva
Despite an array of regulations implemented by governments and social media platforms worldwide (i.e. famous DSA), the problem of digital abusive speech persists. At the same time, rapid advances in NLP and large...
-
Multi-tenant Conversational Analytics ▶ Recording 📝 Transcript
Rodel van Rooijen
Ever wondered how to use GenAI to enable self-service analytics through prompting? In this talk, I will share my experience of building a multi-tenant conversational analytics set-up that is built into a...
-
Taking Control of LLM Outputs: An Introductory Journey into Logits ▶ Recording 📝 Transcript
Emek Gözlüklü
This talk explores logits - the raw confidence scores that language models generate before selecting each token. Understanding and manipulating these scores gives you practical control over how models generate text....