NLP Systems That Can't Tell Use from Mention Censor Counterspeech, but Teaching the Distinction Helps

arXiv:2404.01651v1 Announce Type: new
Abstract: The use of words to convey speaker's intent is traditionally distinguished from the `mention' of words for quoting what someone said, or pointing out properties of a word. Here we show that computationally modeling this use-mention distinction is crucial for dealing with counterspeech online. Counterspeech that refutes problematic content often mentions harmful language but is not harmful itself (e.g., calling a vaccine dangerous is not the same as expressing disapproval of someone for calling vaccines …

abstract arxiv cs.cl cs.cy cs.hc cs.si modeling nlp nlp systems pointing out said show speaker systems teaching type word words