Could a Conversational AI Identify Offensive Language?
  • View Times: 22
  • |
  • Release Date: 2021-12-22
  • offensive
  • dictionary
  • natural language
  • AI ethics
  • fairness
Video Introduction

This video is adapted from 10.3390/info12100418

In recent years, we have seen a wide use of Artificial Intelligence (AI) applications in the Internet and everywhere. Natural Language Processing and Machine Learning are important sub-fields of AI that have made Chatbots and Conversational AI applications possible. Those algorithms are built based on historical data in order to create language models, however historical data could be intrinsically discriminatory. This video investigates whether a Conversational AI could identify offensive language and it will show how large language models often produce quite a bit of unethical behavior because of bias in the historical data. The low-level proof-of-concept will present the challenges to detect offensive language in social media and it will discuss some steps to propitiate strong results in the detection of offensive language and unethical behavior using a Conversational AI.

Full Transcript
1000/1000

Confirm

Are you sure to Delete?
Cite
If you have any further questions, please contact Encyclopedia Editorial Office.
Could a Conversational AI Identify Offensive Language?. Encyclopedia. Available online: https://encyclopedia.pub/video/video_detail/154 (accessed on 13 April 2024).
Could a Conversational AI Identify Offensive Language?. Encyclopedia. Available at: https://encyclopedia.pub/video/video_detail/154. Accessed April 13, 2024.
"Could a Conversational AI Identify Offensive Language?" Encyclopedia, https://encyclopedia.pub/video/video_detail/154 (accessed April 13, 2024).
Encyclopedia. (2021, December 22). Could a Conversational AI Identify Offensive Language?. In Encyclopedia. https://encyclopedia.pub/video/video_detail/154
"Could a Conversational AI Identify Offensive Language?." Encyclopedia. Web. 22 December, 2021.