Läs mer om hur vi framgångsrikt effektiviserat serviceavdelningar i offentlig sektor!
Läs mer om vårt ambitiösa projekt för Sveriges fastighetsbolag!
Säg hej till Jeanett! NetOnNets digitala medarbetare som hanterar köpresan från början till slut.
Elgot är Öresundskrafts digitala medarbetare som revolutionerar sättet energibranschen hanterar kundresan
På Rusta har vi uppnått fantastiska resultat på bara några månader. Läs mer!
After successfully extended a powerful Natural Language Processing (NLP) model called ”SentenceTransformers” to Swedish language, we decided to continue with another exciting project aiming to half-automate the intent training process by grouping similar sentences.
Do you know that not every sentence is useful for the learning process? There is information that we do not want Ebbot to memorize, such as phone numbers, emails and spam messages. That is why we decided to build a Machine Learning (ML) model to classify messages as spam or not spam to filter out unnecessary data.
Based on UKPLab’s publication, we extended the English SentenceTransformers to a Swedish model using TED2020 parallel sentences dataset and achieved 95.6% accuracy.
Hi everyone, my name is Ebbot. Since I started working here at Hello Ebbot, I have received many questions about how I have the ability to interpret human language as a chatbot. There is no short answer for this question, so I wrote this blog to give you an explanation.
In this blog, the NLP team at Hello Ebbot will share all the open-source resources (including models, tools and datasets) that we found specifically serves Swedish – the language that our colleague Ebbot speaks mainly.
A sentiment analysis model with 75% average accuracy specifically trained by Hello Ebbot to classify text data in Swedish.