Can Humans Identify Domains?

arXiv:2404.01785v1 Announce Type: new
Abstract: Textual domain is a crucial property within the Natural Language Processing (NLP) community due to its effects on downstream model performance. The concept itself is, however, loosely defined and, in practice, refers to any non-typological property, such as genre, topic, medium or style of a document. We investigate the core notion of domains via human proficiency in identifying related intrinsic textual properties, specifically the concepts of genre (communicative purpose) and topic (subject matter). We publish …

abstract arxiv community concept core cs.cl document domain domains effects however humans identify language language processing medium natural natural language natural language processing nlp notion performance practice processing property style textual type