What we’re about
Running since 2021, this is leading London meetup group for Natural Language Processing - by practioners, for practioners.
Our focus is sharing the 'how' transformer models and other technologies are used today for language processing in production, and less on the broader theoretical applications of generative AI.
If you have a technical interest in building NLP into your applications, for example using LLMs or small language models with different architectures, and want to meet other experts to share ideas and learnings, then we'd love you to join us.
Our next meeting date is Wednesday 12th June 6-9pm, during London Tech Week in June 2024. If you have a topic you'd like to present, please get in touch.
John & Teo
(With huge gratitude and respect to Heiko for creating this group and building such an awesome community!)
Upcoming events (1)
See all- Unlocking information in the Legal sector using Assistants, VectorDBs, GraphDBsMicrosoft Campus, Paddington, London
Overview:
If you are using LLMs in applications for the Legal sector, then you may come across the challenges of connecting siloed information, building Assistants to automate tasks, and reliably making sense of the semantics of your data.We’re delighted to have three fantastic presentations sharing actionable insights:
- Topic: Understanding Embeddings for the Legal Sector: How AI Distinguishes Among Concepts
Speaker: Jocelyn Matthews from Pinecone
If you had a collection of every kind of animal on earth, from mules to narwhals to goldfish, how would we pick out just the housepets? And how does AI distinguish between a pack mule and a Moscow Mule? Lawyers often need to identify underlying themes or concepts to build arguments, which is akin to how embeddings distil high-dimensional data into lower-dimensional, meaningful representations. Legal professionals are skilled at recognizing fact patterns that may apply across different cases. This is analogous to how embeddings recognize conceptual or contextual similarities in data.
Embeddings are numerical representations that capture the essential features and relationships of objects, like words or images, in a continuous vector space, enabling tasks such as semantic search, clustering, and recommendations. We'll explore the core concepts of embeddings, using relatable examples to make advanced ideas accessible. Legal professionals may find embeddings particularly relevant due to their ability to distinguish between different entities and concepts with nuance. Such capability is crucial for addressing legal issues like precedent analysis, data privacy, bias mitigation, intellectual property, contract review and compliance, legal research, risk management in mergers and acquisitions, and automated redaction of sensitive information.
By understanding how embeddings distinguish between concepts, attendees can draw parallels to their own legal reasoning processes, gaining insights into how these AI mechanisms intersect with legal frameworks. This session encourages legal professionals to explore the intellectual and professional possibilities that embeddings present, deepening an understanding of AI’s role in law. - Topic: TrustGraph: AI Powered Knowledge Graphs Meet Scalable Data Engineering
Speaker: Mark Adams from TrustGraph
Heavily regulated industries often see regulations as a barrier to innovation. When regulations are coupled with disconnected data silos, innovation grinds to a halt. Critical information is buried in thousands of pages - tens of thousands of pages - of technical designs that must couple to regulatory requirements. Whether it’s legal texts, compliance docs, or even industry best practices, connecting these data silos is essential to enabling technical innovation.
In this technical presentation, Mark will provide a brief overview of the TrustGraph open source framework and how it can break down these information barriers and connect the most complex of data silos. The focus will be on demonstrating how TrustGraph deploys reliable, scalable, and accurate AI agents through its modular design and innovative features. Live demo of course! - Topic: What are AI assistants and how can they help me and how can I put AI in production?
Speakers: Christoffer Noring and Liam Hampton from Microsoft
Their talk and demo will cover LLMs, Tool calling, Assistants and also showcase some practical examples where assistants shine. Prepare to be inspired and hopefully get started to create your own AI Assistant. We'll also look into IaC, infrastructure as code, some tooling associated, and how to deploy your apps.
By the end of the meetup we will have gained practical, actionable insights and takeaways that can accelerate development and deployment of NLP in production for Legal applications.
Schedule
18.00: Doors Open
18:00-18.30: Networking (food, drink)
18.30-20.00: Talks
20.00-21.00: More networkingExtra special thanks to our sponsors and speakers:
- Microsoft Reactor for providing the amazing venue
- Pinecone for generously sponsoring food & beverages
About the speakers
- Jocelyn Matthews is Head of Community at Pinecone.
- Mark Adams is Co-Founder and Developer at TrustGraph
- Christoffer Noring and Liam Hampton are Senior Cloud Advocates at Microsoft
- Topic: Understanding Embeddings for the Legal Sector: How AI Distinguishes Among Concepts
