The BERT language model greatly improved the standard for language models. This article explains BERT’s history and the language models derived from it. Anyone who has studied natural language processing (NLP) can tell you that the state of the art moves exceptionally fast. Big players like Google, Facebook, or OpenAI…

Search your large collection of documents in the most effective way using open source tools Semantic search is the task of retrieving documents from a collection of documents (also known as a ‘corpus’) in response to a query asked in natural language. Powered by the latest Transformer language models, semantic…

The data-centric approach to AI leverages your domain expertise to create better machine learning models Data plays a pivotal role in machine learning (ML), AI’s hottest sub-discipline. …

In the last few months we have taken the opportunity to really think about the resources and educational material we want to provide to the Haystack community. Today, I am happy to announce that we have launched a redesigned Haystack website for our developer community! 🥳 The Haystack community has…

Text embeddings represent human language to computers, enabling tasks like semantic search. Here, we introduce sparse and dense vectors in a non-technical way. Here at deepset, our goal is to empower everyone to benefit from the latest advances in natural language processing (NLP). The foundational technology for modern-day NLP is…

In the past few months, our Haystack community has started to grow considerably. With that, we are in a position where we need to think about what type of space we want to provide our community members moving forward. After much consideration, we concluded that we are outgrowing our Slack…

What are they used for? Where can you find them? And what kind of information do they actually store? — Our aim at deepset is that everyone, no matter their level of technical background, can harness the power of modern natural language processing (NLP) and language models for their own use case. Haystack, our open-source framework, makes this a reality. When we talk to our users, we encounter common sources…

Have you ever wondered if extractive QA models contain answers? Read on to learn more! — When people approach natural language processing, and specifically question answering, for the first time, there are a few concepts that cause confusion around models, training them, and the need for data: Will I need to train a model on my own data? Where do the answers come from? And so…

In this article I’ll share with you a cool project some of our cumulians have developed. By the end of it, we achieve a multi-tenant analytics platform where the user not only sees only data relevant to them, but also gets greeted with a theme that is meant for them…