Label-Enhanced Hierarchical Contextualized Representation for Sequential Metaphor Identification

Abstract

Recent metaphor identification approaches mainly consider the contextual text features within a sentence or introduce external linguistic features to the model. But they usually ignore the extra information that the data can provide, such as the contextual metaphor information and broader discourse information. In this paper, we propose a model augmented with hierarchical contextualized representation to extract more information from both sentence-level and discourse-level. At the sentence level, we leverage the metaphor information of words that except the target word in the sentence to strengthen the reasoning ability of our model via a novel label-enhanced contextualized representation. At the discourse level, the position-aware global memory network is adopted to learn long-range dependency among the same words within a discourse. Finally, our model combines the representations obtained from these two parts. The experiment results on two tasks of the VUA dataset show that our model outperforms every other state-of-the-art method that also does not use any external knowledge except what the pre-trained language model contains.

Chinese Metaphorical Relation Extraction: Dataset and Models

“…Metaphor Identification Methods Similar to the construction of the datasets, metaphor identification can be viewed as a word-pair classification problem or a word sequence labeling problem. Most of the current models depend on recurrent neural networks (Do Dinh and Gurevych, 2016;Rei et al, 2017;Gao et al, 2018) and pre-trained language models (Leong et al, 2020;Dankers et al, 2020;Su et al, 2020;Li et al, 2021;Ge et al, 2022;Aghazadeh et al, 2022;Li et al, 2023). (Lee et al, 2017(Lee et al, , 2018, which is a span-based relation extraction model.…”