2023/05/31 by Dmitry Nikolaev, Collin F. Baker, Nikolaev, Dmitry +5
Computer Science · Social Sciences · #Adverb #Ambiguity #Artificial intelligence #Computer science #Epistemology #FrameNet #Language and cultural evolution #Lexical item #Lexical semantics #Linguistics #Meaning (existential) #Natural Language Processing Techniques #Natural language processing #Parsing #Philosophy #Premise #Programming language #Semantic role labeling #Semantics (computer science) #Sentence #Topic Modeling #Verb
paper · pdf · doi:10.48550/arxiv.2305.19650
openalex publication_date 2023/05/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
This paper begins with the premise that adverbs are neglected in computational linguistics. This view derives from two analyses: a literature review and a novel adverb dataset to probe a state-of-the-art language model, thereby uncovering systematic gaps in accounts for adverb meaning. We suggest that using Frame Semantics for characterizing word meaning, as in FrameNet, provides a promising approach to adverb analysis, given its ability to describe ambiguity, semantic roles, and null instantiation.