Towards End-to-End Multilingual Metaphor Processing: Integrating Detection, Translation, and Evaluation

2026-08-04

AI Summary

This work addresses the significant challenge that metaphorical language poses for multilingual natural language processing, as its interpretation and translation require going beyond literal meaning. Existing approaches often treat metaphor detection, machine translation, and translation evaluation as isolated tasks. To overcome this fragmentation, the paper proposes the first end-to-end multilingual metaphor processing framework that unifies all three components within a single computational architecture. By integrating linguistic theory with large language models, the framework employs joint modeling, a novel annotation methodology, and automated evaluation techniques to construct a dedicated dataset and benchmark. This integrated approach substantially enhances both the development efficiency and evaluation accuracy of multilingual NLP systems in handling figurative language.

Abstract

Metaphorical language remains a major challenge for multilingual natural language processing because successful interpretation and translation require reasoning beyond literal lexical meaning. Existing research has largely investigated metaphor detection, machine translation, and translation evaluation as separate tasks, while little work has explored how these components can be integrated into a unified computational framework. This PhD proposal aims to develop an end-to-end framework for multilingual metaphor processing consisting of three complementary research directions: (1) robust metaphor detection across languages, (2) metaphor-oriented translation evaluation for both human assessment and automatic quality estimation, and (3) joint modelling that connects metaphor detection with translation evaluation. The proposed research will combine linguistic theory with recent advances in large language models to develop new datasets, annotation methodologies, evaluation benchmarks, and automatic evaluation approaches for metaphor-aware machine translation. The expected outcome is a unified framework that improves both the development and evaluation of multilingual NLP systems when processing figurative language.

Problem

• metaphor processing
• multilingual NLP
• machine translation
• translation evaluation
• figurative language

Innovation

• multilingual metaphor processing
• end-to-end framework
• metaphor detection
• metaphor-aware machine translation
• translation evaluation