The Symanto Brain extension enables you to easily and efficiently build custom text analytics models within KNIME in a matter of minutes. It is powered by a comprehensive, in-house pre-trained Transformer model, advanced NLP techniques, and machine learning algorithms that allow you to extract insights from your text data and make data-driven decisions. The extension overcomes the limitations of pre-built models and elevates text analytics capabilities, thereby enhancing the value of your text data, all within the KNIME platform.

The Symanto Brain extension is the result of extensive data utilisation, which grants it robust functionality across more than 50 languages, diverse tasks such as sentiment analysis, emotion detection, and topic categorisation, and multiple data sources including customer service data, social media, reviews, and news articles.

Here is a link to our detailed how-to-use guide: Symanto Brain KNIME Extension

In case you are experiencing any issues using the Symanto Brain extension, please contact our support team at support@symanto.com.

How to get access

Once your account is verified, please go to the free trial section to get your free key, which you can afterwards find in your profile section.

Options

Pattern

Specify the pattern the model wants to use. (e.g., this person talk about {}). Your pattern must contain{}.

Langauge

Language is the content of the text.
Supported languages: ar, bg, ca, cs, da, de, el, en, es, et, fa, fi, fr, gl, gu, he, hi, hr, hu, hy, id, it, ja, ka, ko, ku, lt, lv, mk, mn, mr, ms, my, nb, nl, pl, pt, pt, pt-br, ro, ru, sk, sl, sq, sr, sv, th, tr, uk, ur, vi, zh

Model

Model you want to use.
symanto_brain_multilanguage: model that supports multilanguage.
symanto_brain_german: specially trained model for German.
symanto_brain_english: specially trained model for English.

Text Column

Select the column containing the text from the list.

Multi Label

if false, returned probability distribution among provided labels for each instance will sum up to 1. Otherwise it will be unnormalized.

Views

This node has no views

Workflows

• Zero-shot classification on the Lifestyle topics for performing Hyper-segmentationKNIME Hub
• Zero-shot text classification and evaluation for Emotion AnalysisKNIME Hub
• Zero-shot text classification and evaluation for Sentiment Analysis in EnglishKNIME Hub
• Zero-shot text classification and evaluation for Sentiment Analysis in GermanKNIME Hub
• Zero-shot text classification and evaluation for Sentiment Analysis in SpanishKNIME Hub
• Show all 6 workflows

Links

• No links available

Developers