Get the latest tech news
Neural network trained on 'Friends' can detect sarcasm 75% of the time
Researchers say their new algorithm trained on a database of TV show clips can detect sarcasm 75% of the time.
Back in 2019, when AI was safely in the realm of science fiction and GPT-2 was still several months from release, a group of researchers submitted a paper to that summer’s annual meeting of the Association for Computational Linguistics. The original MUStARD paper identifies several examples of such cues—”a change of tone, overemphasis [on] a word, a drawn-out syllable, or a straight-looking face”—and argues that such “multimodal” analysis is essential for parsing sarcasm correctly. A short abstract of the research published on the meeting site explains how the model works: the words from audio data are extracted with automatic speech recognition, and are then assigned an emoticon to denote their underlying sentiment.
Or read this on Hacker News
