# MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories

Source: [MelBERT: Metaphor Detection via Contextualized Late Interaction using Metaphorical Identification Theories](<https://www.sota2.com/research/paper/68fa69d71e209131cea2489d>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T23:10:38.141Z

Authors: Minjin Choi, Sunkyung Lee, Eunseong Choi, Heesoo Park, Junhyuk Lee, Dongwon Lee, Jongwuk Lee

Published: 2021-04-28T07:52:01.000Z

## Abstract

Automated metaphor detection is a challenging task to identify metaphorical expressions of words in a sentence. To tackle this problem, we adopt pre-trained contextualized models, e.g., BERT and RoBERTa. To this end, we propose a novel metaphor detection model, namely metaphor-aware late interaction over BERT (MelBERT). Our model not only leverages contextualized word representation but also benefits from linguistic metaphor identification theories to distinguish between the contextual and literal meaning of words. Our empirical results demonstrate that MelBERT outperforms several strong baselines on four benchmark datasets, i.e., VUA-18, VUA-20, MOH-X, and TroFi.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Metaphor Prediction on VUA 18](<https://www.sota2.com/research/sota/metaphor-prediction-on-vua-18.md>): Metaphor Prediction; VUA 18; Accuracy: 93.8.

- [Metaphor Prediction on VUA-18 (test)](<https://www.sota2.com/research/sota/metaphor-prediction-on-vua-18-test.md>): Metaphor Prediction; VUA-18 (test); Binary F1: 78.2.

- [Metaphor detection on MOH-X](<https://www.sota2.com/research/sota/metaphor-detection-on-moh-x.md>): Metaphor Detection; MOH-X; F1 Score: 80.6.

- [Metaphor Detection on TroFi](<https://www.sota2.com/research/sota/metaphor-detection-on-trofi.md>): Metaphor Detection; TroFi; F1 Score: 63.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2104.13615>)

[PDF](<https://arxiv.org/pdf/2104.13615.pdf>)
