Getting the Most out of Simile Recognition

Xiaoyue Wang, Linfeng Song, Xin Liu, Chulun Zhou, Hualin Zeng, Jinsong Su

Abstract

Simile recognition involves two subtasks: simile sentence classification that discriminates whether a sentence contains simile, and simile component extraction that locates the corresponding objects (i.e., tenors and vehicles).Recent work ignores features other than surface strings and suffers from the data hunger issue.We explore expressive features for this task to help achieve more effective data utilization.In particular, we study two types of features: 1) input-side features that include POS tags, dependency trees and word definitions, and 2) decoding features that capture the interdependence among various decoding decisions.We further construct a model named HGSR, which merges the input-side features as a heterogeneous graph and leverages decoding features via distillation.Experiments show that HGSR significantly outperforms the current state-of-the-art systems and carefully designed baselines, verifying the effectiveness of introduced features. We will release our code upon paper acceptance.
BibTeX
@inproceedings{wang2022getting,
  author = {Xiaoyue Wang and Linfeng Song and Xin Liu and Chulun Zhou and Hualin Zeng and Jinsong Su},
  title = {{Getting the Most out of Simile Recognition}},
  booktitle = {Conference on Empirical Methods in Natural Language Processing},
  year = {2022},
  doi = {10.18653/v1/2022.findings-emnlp.236},
}
Figure