Tracing metaphors in time through self-distance in vector spaces
This addresses the challenge of tracing semantic change for linguists and computational researchers, though it is incremental as it applies existing vector space methods to a specific linguistic task.
The study tackled the problem of detecting the emergence of metaphorical senses in language by analyzing changes in word similarity over time in a diachronic corpus of Italian, finding that drops in self-similarity correlate with documented metaphorical shifts.
From a diachronic corpus of Italian, we build consecutive vector spaces in time and use them to compare a term's cosine similarity to itself in different time spans. We assume that a drop in similarity might be related to the emergence of a metaphorical sense at a given time. Similarity-based observations are matched to the actual year when a figurative meaning was documented in a reference dictionary and through manual inspection of corpus occurrences.