Metaphor Detection using Deep Contextualized Word Embeddings
This addresses the problem of automating metaphor detection for natural language processing tasks, but it is incremental as it builds on existing deep learning techniques.
The paper tackled metaphor detection in natural language by proposing an end-to-end method using deep contextualized word embeddings, bidirectional LSTMs, and multi-head attention, which outperformed existing baselines on benchmark datasets TroFi and MOH-X.
Metaphors are ubiquitous in natural language, and their detection plays an essential role in many natural language processing tasks, such as language understanding, sentiment analysis, etc. Most existing approaches for metaphor detection rely on complex, hand-crafted and fine-tuned feature pipelines, which greatly limit their applicability. In this work, we present an end-to-end method composed of deep contextualized word embeddings, bidirectional LSTMs and multi-head attention mechanism to address the task of automatic metaphor detection. Our method, unlike many other existing approaches, requires only the raw text sequences as input features to detect the metaphoricity of a phrase. We compare the performance of our method against the existing baselines on two benchmark datasets, TroFi, and MOH-X respectively. Experimental evaluations confirm the effectiveness of our approach.