Improvements and Extensions on Metaphor Detection
This work provides improved metaphor detection capabilities for natural language understanding researchers, with incremental gains on existing benchmarks.
This paper introduces a pre-trained Transformer-based model for metaphor detection (MD), achieving significant F-1 score improvements ranging from 5.33% to 28.39% over previous state-of-the-art models. Additionally, the authors extend MD to classify metaphoricity for entire texts and clean up outdated annotations in a benchmark dataset.
Metaphors are ubiquitous in human language. The metaphor detection task (MD) aims at detecting and interpreting metaphors from written language, which is crucial in natural language understanding (NLU) research. In this paper, we introduce a pre-trained Transformer-based model into MD. Our model outperforms the previous state-of-the-art models by large margins in our evaluations, with relative improvements on the F-1 score from 5.33% to 28.39%. Second, we extend MD to a classification task about the metaphoricity of an entire piece of text to make MD applicable in more general NLU scenes. Finally, we clean up the improper or outdated annotations in one of the MD benchmark datasets and re-benchmark it with our Transformer-based model. This approach could be applied to other existing MD datasets as well, since the metaphoricity annotations in these benchmark datasets may be outdated. Future research efforts are also necessary to build an up-to-date and well-annotated dataset consisting of longer and more complex texts.