Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ContrastWSD: Enhancing Metaphor Detection with Word Sense Disambiguation Following the Metaphor Identification Procedure

Mohamad Elzohbi, Richard Zhao

TL;DR

This paper presents ContrastWSD, a RoBERTa-based metaphor detection model that integrates the Metaphor Identification Procedure and Word Sense Disambiguation to extract and contrast the contextual meaning with the basic meaning of a word to determine whether it is used metaphorically in a sentence.

Abstract

This paper presents ContrastWSD, a RoBERTa-based metaphor detection model that integrates the Metaphor Identification Procedure (MIP) and Word Sense Disambiguation (WSD) to extract and contrast the contextual meaning with the basic meaning of a word to determine whether it is used metaphorically in a sentence. By utilizing the word senses derived from a WSD model, our model enhances the metaphor detection process and outperforms other methods that rely solely on contextual embeddings or integrate only the basic definitions and other external knowledge. We evaluate our approach on various benchmark datasets and compare it with strong baselines, indicating the effectiveness in advancing metaphor detection.

ContrastWSD: Enhancing Metaphor Detection with Word Sense Disambiguation Following the Metaphor Identification Procedure

TL;DR

This paper presents ContrastWSD, a RoBERTa-based metaphor detection model that integrates the Metaphor Identification Procedure and Word Sense Disambiguation to extract and contrast the contextual meaning with the basic meaning of a word to determine whether it is used metaphorically in a sentence.

Abstract

This paper presents ContrastWSD, a RoBERTa-based metaphor detection model that integrates the Metaphor Identification Procedure (MIP) and Word Sense Disambiguation (WSD) to extract and contrast the contextual meaning with the basic meaning of a word to determine whether it is used metaphorically in a sentence. By utilizing the word senses derived from a WSD model, our model enhances the metaphor detection process and outperforms other methods that rely solely on contextual embeddings or integrate only the basic definitions and other external knowledge. We evaluate our approach on various benchmark datasets and compare it with strong baselines, indicating the effectiveness in advancing metaphor detection.
Paper Structure (15 sections, 3 equations, 2 figures, 5 tables)

This paper contains 15 sections, 3 equations, 2 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Data Augmentation
  5. Model Structure
  6. Experiments
  7. Datasets:
  8. Baselines:
  9. Experimental Setup
  10. Empirical Results and Case Studies
  11. Statistical Significance
  12. Overall Results
  13. Case Studies:
  14. Conclusion and Future Work
  15. Bibliographical References

Figures (2)

  • Figure 1: The Metaphor Identification Procedure
  • Figure 2: ContrastWSD overall framework showing both stages: (i) the data augmentation stage and (ii) the metaphor detection stage.