Lazar \u0110okovi\u0107 and Marko Robnik-\u0160ikonja<\/p>\n
Abstract
The sarcasm detection task in natural language processing tries
to classify whether an utterance is sarcastic or not. It is related
to sentiment analysis since it often inverts surface sentiment. Because sarcastic sentences are highly dependent on context, and
they are often accompanied by various non-verbal cues, the task
is challenging. Most of related work focuses on high-resourced
languages like English. To build a sarcasm detection dataset for
a less-resourced language, such as Slovenian, we leverage two
modern techniques: a machine translation specific medium-size
transformer model, and a very large generative language model.
We explore the viability of translated datasets and how the size of
a pretrained transformer affects its ability to detect sarcasm. We
train ensembles of detection models and evaluate models\u2019 performance. The results show that larger models generally outperform
smaller ones and that ensembling can slightly improve sarcasm
detection performance. Our best ensemble approach achieves an
F1-score of 0.765 which is close to annotators\u2019 agreement in the
source language.<\/p>\n
\u00a0<\/p>\n\n\n\n