"Did I Say Something Wrong?": Towards a Safe Collaborative Chatbot

AAAI 2018 pp. 8067-8068

doi:10.1609/AAAI.V32I1.12145 /aaai/2018/chkroun2018aaai-say/

Abstract

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 platform that enables users to collaboratively teach a chatbot responses, using natural language. We present a method of collectively detecting malicious users and using the commands taught by these users to further mitigate activity of future malicious users.

PDF AAAI Semantic Scholar

Cite

Text

Chkroun and Azaria. ""Did I Say Something Wrong?": Towards a Safe Collaborative Chatbot." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.12145

Markdown

[Chkroun and Azaria. ""Did I Say Something Wrong?": Towards a Safe Collaborative Chatbot." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/chkroun2018aaai-say/) doi:10.1609/AAAI.V32I1.12145

BibTeX

@inproceedings{chkroun2018aaai-say,
  title     = {{"Did I Say Something Wrong?": Towards a Safe Collaborative Chatbot}},
  author    = {Chkroun, Merav and Azaria, Amos},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {8067-8068},
  doi       = {10.1609/AAAI.V32I1.12145},
  url       = {https://mlanthology.org/aaai/2018/chkroun2018aaai-say/}
}