Papers by Marco Fisichella

1 papers
Toxicity, Morality, and Speech Act Guided Stance Detection (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing studies that focus on stance detection ignore the speech act, toxic, and moral features of tweets or lack an efficient architecture to detect the attitudes across targets.
Approach: They propose a multitasking model that extracts valence, arousal, and dominance aspects hidden in tweets and injects the emotional sense into the embedded text followed by an efficient attention framework to correctly detect the tweet’s stance.
Outcome: The proposed model exploits the toxicity, morality, and speech act features of the tweets to detect the public's stance.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations