LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL LOEBNER 2013 FINALIST SELECTION CHAT TEST RESULTS ====================================== ChatBot Correct Correct Human-like Human-like Responses Responses (Points) (% of total) 4 FINALISTS: ====================================== Izar 18.5 92.5 Mitsuku 18.0 90.0 Tutor 17.0 85.0 Rose 15.0 75.0 ====================================== CHATTERS UP: ====================================== Uberbot 1.0 14.5 72.5 Cleverbot 13.5 67.5 Alice2 13.0 65.0 Arckon (Mark) 13.0 65.0 Aidan 1.1.20 12.5 62.5 The_professor 11.5 57.5 UltraHal 10.5 52.5 Zoe 10.5 52.5 Talk2me 8.0 40.0 Johnny 4.0 20.0 Robocrates 1.5 7.2 ======================================= SCORING SYSTEM: 1 point for a correct & human-like answer, 0.5 for a partially correct & human-like answer, 0 points otherwise. LLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLLL