论文信息 - Safebot: A Safe Collaborative Chatbot

Safebot: A Safe Collaborative Chatbot

Chatbots have been a core measure of AI since Turing has presented his test for intelligence, and are also widely used for entertainment purposes. In this paper we present a plat- form that enables users to collaboratively teach a chatbot responses, using natural language. We present a method of col- lectively detecting malicious users and using the commands taught by the malicious users to further mitigate activity of future malicious users. We ran an experiment with several subjects, playing different roles, showing the effectiveness of our chatbot.

Amos Azaria | Merav Chkroun | Amos Azaria | Merav Chkroun

[1] Daniel G. Goldstein,et al. VoxPL: Programming with the Wisdom of the Crowd , 2017, CHI.

[2] Gina Neff,et al. Talking to Bots: Symbiotic Agency and the Case of Tay , 2016 .

[3] Amos Azaria,et al. Recommender Systems with Personality , 2016, RecSys.

[4] Amos Azaria,et al. InstructableCrowd: Creating IF-THEN Rules via Conversations with the Crowd , 2016, CHI Extended Abstracts.

[5] Amos Azaria,et al. Instructable Intelligent Personal Agent , 2016, AAAI.

[6] Amos Azaria,et al. The DARPA Twitter Bot Challenge , 2016, Computer.

[7] Omer Levy,et al. word2vec Explained: deriving Mikolov et al.'s negative-sampling word-embedding method , 2014, ArXiv.

[8] Ulrike Spierling. 'Killer Phrases': Design Steps for a Game with Digital Role-Playing Agents , 2008, Trans. Edutainment.

[9] Ming Zhou,et al. Extracting Chatbot Knowledge from Online Discussion Forums , 2007, IJCAI.

[10] J. Weizenbaum. From Computer Power and Human Reason From Judgment to Calculation , 2007 .

[11] John Sloan,et al. Wisdom of the crowd , 2005, Nature.

[12] Michael L. Mauldin,et al. CHATTERBOTS, TINYMUDS, and the Turing Test: Entering the Loebner Prize Competition , 1994, AAAI.