We’re proud to announce the release of our new Italian Native Language Pack. This makes Italian the seventh language currently supported by Lexalytics.
We put great pride and emphasis on our native language approach; our language support relies on understanding how the language is put together and understood by native speakers. Knowing how a language is constructed is crucial for the accuracy of part-of-speech tagging, the foundation of our text analytics.
As with all our language packs, we enlist native language speakers to develop our out-of-the-box sentiment files and provide annotations of people, companies, places, and products within Italian content for our entity model training. This native approach ensures that our software catches the nuances of the language that would be otherwise lost through translation.
This new addition comes on the heels of the release of Spanish and Portuguese version two. The main focus of the update was expanding the sentiment phrase dictionaries so the language packs have as much out-of-the-box utility as possible.