TNT KID Text on demonstrator page
updated text including Slovenian TNT-KID (Croatian, Estonian, Latvian, Slovenian, English)
TNT-KID is a system for automatic keyword extraction. It was trained on a corpus of articles with human-assigned keywords. For Croatian the annotators were 24sata editors, for Estonian the Ekspress Meedia staff and for Latvian the Latvian Delfi staff. For Slovenian and English, public datasets were used. More info (including how to train the system on your data or language) is available HERE (HERE->insert clickable link: https://github.com/EMBEDDIA/tnt_kid). For Estonian and Latvian, the results of TNT-KID are expanded by tagset matching (as explained HERE). (HERE-> insert clickable link:https://aclanthology.org/2021.hackashop-1.4/).