<img src="assets/taranis-logo.svg" style="height: 4em; width: auto; margin-bottom: 2em;" alt="Taranis Logo" /> ## Named Entity Recognition with Taranis AI <div style="display: flex; justify-content: center; gap: 2em; align-items: center;"> <span style="display: inline-flex; align-items: center; gap: 0.5em;"> <img src="assets/github.svg" alt="" style="height: 1.8em;"> <a href="https://github.com/taranis-ai/taranis-ai">taranis-ai/taranis-ai</a> </span> </div> Note: --- ## PPN Dataset <a href="https://github.com/hybrinfox/ppn">https://github.com/hybrinfox/ppn</a> # Statistics | Language | Number of documents |---|--: | Arabic | 1 079 | Chinese | 794 |English | 3 219 | French | 4 141 | German | 3 341 |Italian | 1 796 |Russian | 1 435 | Spanish | 2 485 | Ukrainian | 439 | **Total** | 18 729 --- <div style="flex: 1; min-width: 300px; margin-top: -150px"> ## Named Entity Recognition - **Lists and Regex** - CVEs, APT Groups, Hashes - **NER** - Person, Location, Organization, Product, Event </div> Note: At this screenshot Taranis highlights key entities automatically. CVEs, APTs, people, companies — all annotated. This dual approach lets us tune for performance and accuracy. Regex when it’s structured. Models when it’s not. --- <img src="assets/ner_bot.png" alt="NER Bot" style="max-width: 100%; margin-top: -2em;"> --- <img src="assets/taranis_story.png" alt="Taranis Story" style="max-width: 100%;"> --- <img src="assets/assess.png" alt="Assess" style="max-width: 100%;"> --- <img src="assets/named_entity_recognition_final.svg" alt="Named Entity Recognition" style="max-width: 100%;"> --- ## Live Demo