TL;DR
This study explores how different temporal and static word embeddings affect metaphor detection, revealing that temporal embeddings can sometimes blur core and contextual meanings, with minimal impact observed on current benchmarks.
Contribution
It is the first detailed analysis examining the influence of temporal language evolution on metaphor detection using various word embeddings.
Findings
Different static embeddings impact metaphor detection.
Temporal embeddings sometimes outperform static methods.
Temporal embeddings may blur core and contextual meanings.
Abstract
State-of-the-art approaches for metaphor detection compare their literal - or core - meaning and their contextual meaning using metaphor classifiers based on neural networks. However, metaphorical expressions evolve over time due to various reasons, such as cultural and societal impact. Metaphorical expressions are known to co-evolve with language and literal word meanings, and even drive, to some extent, this evolution. This poses the question of whether different, possibly time-specific, representations of literal meanings may impact the metaphor detection task. To the best of our knowledge, this is the first study that examines the metaphor detection task with a detailed exploratory analysis where different temporal and static word embeddings are used to account for different representations of literal meanings. Our experimental analysis is based on three popular benchmarks used for…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsTemporal Word Embeddings with a Compass
