Multi-Label Text classification model used to decode if passages contain a misfortunate event, a cause for misfortune, and/or an action to mollify or prevent some misfortune. The current F1 micro score of 140 passages not used for training is .678. individual class f1 scores shown below. <ul> <li>EVENT: .916 <ul> <li> Illness: .870 </li> <li> Accident: .0 </li> <li> Other: .0 </li> </ul> </li> <li>CAUSE: .863 <ul> <li> Just Happens: .870 </li> <li> Material Physical: .0 </li> <li> Spirits and Gods: .718 </li> <li> Witchcraft and Sorcery: .0 </li> <li> Rule Violation Taboo: .0 </li> <li> Jealous Evil Eye: .0 </li> </ul> </li> <li>ACTION: .766 <ul> <li> Physical Material: .538 </li> <li> Technical Specialist: .0 </li> <li> Divination: .0 </li> <li> Shaman Medium Healer: .08 </li> <li> Priest High Religion: .0 </li> <li> Other: .0 </li> </ul> </li> </ul>

<br><br><br> For a quick demo, try typing in a sentence or even a paragraph in the <b>Hosted inference API</b> then pressing "compute"!