Non-English Tools for Rasa NLU
Rasa
by Vincent Warmerdam
2y ago
The Rasa community spans the globe, so we often get questions on optimising a Rasa pipeline for a wide variety of languages. Rasa is designed to be customisable and we do our best to support as many languages as possible. Over the years there’s also been a number of plugins and community projects that add components for Non-English use cases. This blog post aims to give an overview of these tools to help you build Non-English assistants. We’ve split up the document into different sections that each highlight a different part of the NLU pipeline. We’ll start with tokenisers, move on to featuri ..read more
Visit website
Custom Rasa NLU Docker Containers
Rasa
by Vincent Warmerdam
2y ago
The main use-case for Rasa NLU pipelines is to construct virtual assistants. That said, the intents and entities that Rasa can predict are based on domain knowledge that can also be reused across an organisation. Detecting a frequently asked question is useful for a virtual assistant, but it can also be useful as an API for customer service. This guide will briefly highlight how Rasa's NLU models can be hosted as an independent API. We'll also go the extra mile by showing you how you can wrap it all in a customisable docker container. Rasa NLU as an API When you run `rasa train` from the comm ..read more
Visit website
Prioritise Labelling with the UnexpecTEDIntentPolicy
Rasa
by Vincent Warmerdam
2y ago
Let’s say you’ve got an assistant running in production. It turned out that it’s a popular interface so lots of users are interacting with it. You’d like to learn from all these interactions so you set yourself up to start labelling. This can be intimidating though. Especially when your assistant is popular, you’re bound to have many conversation logs to go through. Even with a large team, going through every conversation can be a daunting task. This is what it might feel like. Instead of going through every conversation, it would be better to have a system that can help you prioritize which ..read more
Visit website
Announcing the Conversational AI with Rasa series
Rasa
by Justina Petraityte
2y ago
We are extremely excited to announce our brand new series on our Rasa Youtube channel - Conversational AI with Rasa. It’s a 14-episode series focused on developing AI assistants with Rasa Open Source (version 2.x and later). Each episode is dedicated to a specific topic and combines theoretical information with code examples and demos. This series is for anyone interested in learning all fundamentals of developing an AI assistant with Rasa Open Source. We dive into each topic in great detail so this series is beginner friendly, but we are sure that experienced Rasa developers will also learn ..read more
Visit website
Conditional Response Variations: Technical Blog
Rasa
by Anca Lita
2y ago
Introduction As part of the Rasa Open Source 2.6 release, we introduced a new feature called conditional response variations which allows slot-values to determine when a particular response variation is used by your bot. If you haven’t heard about this feature, we recommend checking out our introductory blog post. In this blog we plan to cover: using conditional response variations to reduce the number of training stories, understanding the variation selection criteria for complex responses with conditional response variations, channels, and default responses, and guidance for responsible an ..read more
Visit website
Now Available in Rasa Open Source: Conditional Response Variations
Rasa
by Karen White
3y ago
We’re excited to announce the experimental release of conditional response variations, now available in Rasa Open Source 2.6. Conditional response variations allow your assistant to serve the end user a different response based on slot values, creating personalized conversations. This enables an assistant to reply to the user with a special response if a customer’s subscription tier is Premium, a user’s location is Canada or a customer’s upgrade eligibility is true. In the past, creating conditional responses required custom actions or multiple stories. With this release, conditional response ..read more
Visit website
Custom SpaCy 3.0 models in Rasa
Rasa
by Vincent Warmerdam
3y ago
This guide was written for Rasa version 2.6.2 with spaCy version 3.0.6. Let’s say that you’re a financial organisation interested in building a virtual assistant. The virtual assistant will likely need to be able to detect certain entities: dates, bank accounts, addresses, as well as financial jargon related to mortgages. Odds are though, it’s not just your virtual assistant that needs to detect  these entities. This capability will also be relevant for other use cases in your organisation, like contract parsing, automated email forwarding in customer service and detecting fraud. It ther ..read more
Visit website
Rasa Developer Survey 2021 is now open!
Rasa
by Justina Petraityte
3y ago
Hello Rasa Community! We are continuing our efforts to understand our community better and are very excited to share the Rasa Developer Survey 2021 with you!  It’s a survey of 32 quick questions which will take you about 5 minutes to complete. This year we continue to learn about your technical background, the ways you use Rasa and interact with other tools and open source communities. In addition to that we added a few diversity and inclusion related questions. We will share the aggregated and anonymized survey results with you once the survey is closed. You can take the survey here. A ..read more
Visit website
L3-AI Speaker Interview: Greg Bennett
Rasa
by Rasa
3y ago
In the leadup to the L3-AI conference on June 17, we recently caught up with Greg Bennett, speaker and Conversational Design Principal at Salesforce. In this interview, we covered a number of topics around best practices for customers in the conversational AI space and how Salesforce thinks about new features, conversational UX, and where the industry is going next. Enjoy! Watch Greg’s talk - plus many more from NLP researchers, product experts, and machine learning engineers - at L3-AI. Tickets are free and registration is open now. What impact do chat and voice assistants have on the busine ..read more
Visit website
Rasa X Two Years Later: CDD, Data, and What it Means for Customer Experience
Rasa
by Alan Nichol
3y ago
I’m reflecting on how the market and product have evolved since Rasa X was released two years ago. For one, we are seeing a significant (and overdue!) shift in how enterprises value AI work. Advanced teams now view training data as the primary contributor to building AI that delivers results. In parallel, our product has evolved from serving individual technical practitioners to an enterprise platform for practicing conversation-driven development.  Enterprises now know that quality training data is a key differentiator for customer experience, and have the tools to acquire it efficientl ..read more
Visit website

Follow Rasa on FeedSpot

Continue with Google
Continue with Apple
OR