Abstract
The contrast between the contextual and general meaning of a word serves as an important clue for detecting its metaphoricity. In this paper, we present a deep neural architecture for metaphor detection which exploits this contrast. Additionally, we also use cost-sensitive learning by re-weighting examples, and baseline features like concreteness ratings, POS and WordNet-based features. The best performing system of ours achieves an overall F1 score of 0.570 on All POS category and 0.605 on the Verbs category at the Metaphor Shared Task 2018.
Cite
CITATION STYLE
Swarnkar, K., & Singh, A. K. (2018). Di-LSTM contrast: A deep neural network for metaphor detection. In Proceedings of the Workshop on Figurative Language Processing, Fig-Lang 2018 at the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HTL 2018 (pp. 115–120). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w18-0914
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
