A Call for Standardization and Validation of Text Style Transfer Evaluation
This work addresses inconsistent evaluation practices in the Text Style Transfer field, which is an incremental improvement aimed at researchers in natural language processing.
The paper identifies a lack of standardization and validation in Text Style Transfer evaluation, revealing gaps in both human and automated methods through a meta-analysis of existing literature.
Text Style Transfer (TST) evaluation is, in practice, inconsistent. Therefore, we conduct a meta-analysis on human and automated TST evaluation and experimentation that thoroughly examines existing literature in the field. The meta-analysis reveals a substantial standardization gap in human and automated evaluation. In addition, we also find a validation gap: only few automated metrics have been validated using human experiments. To this end, we thoroughly scrutinize both the standardization and validation gap and reveal the resulting pitfalls. This work also paves the way to close the standardization and validation gap in TST evaluation by calling out requirements to be met by future research.