Evaluating the Evaluation Metrics for Style Transfer: A Case Study in Multilingual Formality Transfer
arXiv:2110.10668
Abstract
While the field of style transfer (ST) has been growing rapidly, it has been hampered by a lack of standardized practices for automatic evaluation. In this paper, we evaluate leading ST automatic metrics on the oft-researched task of formality style transfer. Unlike previous evaluations, which focus solely on English, we expand our focus to Brazilian-Portuguese, French, and Italian, making this work the first multilingual evaluation of metrics in ST. We outline best practices for automatic evaluation in (formality) style transfer and identify several models that correlate well with human judgments and are robust across languages. We hope that this work will help accelerate development in ST, where human evaluation is often challenging to collect.
arXiv commentEMNLP 2021
References in corpus (7)
- Efficient Estimation of Word Representations in Vector Space
- A Probabilistic Formulation of Unsupervised Text Style Transfer
- Style Transfer for Texts: Retrain, Report Errors, Compare with Rewrites
- Formality Style Transfer with Hybrid Textual Annotations
- Style-transfer and Paraphrase: Looking for a Sensible Semantic Similarity Metric
- SQUINKY! A Corpus of Sentence-level Formality, Informativeness, and Implicature
- Grammatical Error Correction and Style Transfer via Zero-shot Monolingual Translation