Adverbs, Surprisingly
This work tackles the problem of understudied adverbs in computational linguistics, offering an incremental contribution by applying existing Frame Semantics methods to a new linguistic domain.
The paper addresses the neglect of adverbs in computational linguistics by analyzing literature and probing a state-of-the-art language model with a novel adverb dataset, revealing systematic gaps in adverb meaning accounts. It proposes using Frame Semantics, specifically FrameNet, as a promising approach due to its ability to handle ambiguity, semantic roles, and null instantiation.
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.