Language support for NLP
Pega Platform provides text analytics based on natural language processing (NLP) that you can use to detect, process, and structure text data from email, chatbots, and social media platforms. Depending on the language of the analyzed content, various text analytics features help you obtain accurate analysis results.
The Pega-NLP ruleset supports 16 languages for analysis. You can create text models in Pega Platform and use them to analyze texts. Some NLP features are only available for certain languages, as shown in the following table.
Before you configure your text models, define the languages that you want to use for NLP. For more information, see Enabling languages for NLP.
Languages that Pega Platform can analyze
|Language||Continuous learning||Text extraction||Topic detection||Small talk detection||Intent analysis||Sentiment analysis|
|Croatian||✓||✓||✓||Not available||Not available||Not available|
|Czech||✓||✓||✓||Not available||Not available||Not available|
|Danish||✓||✓||✓||Not available||Not available||Not available|
|Japanese||✓||✓||✓||Not available||Not available||Not available|
|Norwegian||✓||✓||✓||Not available||Not available||Not available|
|Polish||✓||✓||✓||Not available||Not available||Not available|
|Russian||✓||✓||✓||Not available||Not available||Not available|
|Swedish||✓||✓||✓||Not available||Not available||Not available|
|Turkish||✓||✓||✓||Not available||Not available||Not available|
- Enabling languages for NLP
Pega Platform provides natural language processing (NLP) features for various languages. Define the languages that you want to analyze in text models that you create in Pega Platform.
- Setting up a keyword-based topic detection model
Create a keyword-based topic detection model by specifying the model name, language, and corresponding ruleset. After you create the model, complete the model configuration by defining a taxonomy of topics and keywords.
- Setting up a machine-learning topic detection model
Start the build process of a keyword-based topic detection model by specifying the model name, language, and corresponding ruleset.
- Configuring advanced text analytics settings
Configure language detection settings, enable spell checking, and control how the text is categorized, based on various criteria.
- Sentiment lexicons
A sentiment lexicon is a list of semantic features for words and phrases. Use lexicons for creating machine learning-based sentiment and intent analysis models.