Sarcasm Detection with External Entity Information

11 pages•Published: September 20, 2022

Abstract

Sarcasm is generally characterized as ironic or satirical that is intended to blame, mock, or amuse in an implied way. Recently, pre-trained language models, such as BERT, have achieved remarkable success in sarcasm detection. However, there are many problems that cannot be solved by using such state-of-the-art models. One problem is attribute infor- mation of entities in sentences. This work investigates the potential of external knowledge about entities in knowledge bases to improve BERT for sarcasm detection. We apply em- bedded knowledge graph from Wikipedia to the task. We generate vector representations from entities of knowledge graph. Then we incorporate them with BERT by a mechanism based on self-attention. Experimental results indicate that our approach improves the accuracy as compared with the BERT model without external knowledge.

Keyphrases: knowledge graph, pre trained model, sarcasm detection

In: Tokuro Matsuo (editor). Proceedings of 11th International Congress on Advanced Applied Informatics, vol 81, pages 121-131.

Links:	https://easychair.org/publications/paper/kxKL
	https://doi.org/10.29007/zbzq

BibTeX entry

@inproceedings{IIAIAAI2021-Winter:Sarcasm_Detection_with_External,
  author    = {Xu Xufei and Shimada Kazutaka},
  title     = {Sarcasm Detection with External Entity Information},
  booktitle = {Proceedings of 11th International Congress on Advanced Applied Informatics},
  editor    = {Tokuro Matsuo},
  series    = {EPiC Series in Computing},
  volume    = {81},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/kxKL},
  doi       = {10.29007/zbzq},
  pages     = {121-131},
  year      = {2022}}

Download PDF Open PDF in browser