في حين أن مجال نقل النمط (ST) ينمو بسرعة، فقد أعاقه بعدم وجود ممارسات موحدة للتقييم التلقائي.في هذه الورقة، نقوم بتقييم المقاييس التلقائية الرائدة على المهمة التي تم بحثها عن نقل أسلوب الأشكال.على عكس التقييمات السابقة، التي تركز فقط على اللغة الإنجليزية فقط، فإننا نوسع تركيزنا على البرتغالية البرازيلية والفرنسية والإيطالية، مما يجعل هذا العمل أول تقييم متعدد اللغات للمقاييس في القديس.نحن نخوض أفضل الممارسات للتقييم التلقائي في نقل النمط (الشكلية) وتحديد العديد من النماذج التي ترتبط بشكل جيد مع الأحكام البشرية وهي قوية عبر اللغات.نأمل أن يساعد هذا العمل في تسريع التطوير في القديس، حيث يكون التقييم البشري غالبا ما يكون تحديا لجمعه.
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 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.
References used
https://aclanthology.org/
This paper reviews and summarizes human evaluation practices described in 97 style transfer papers with respect to three main evaluation aspects: style transfer, meaning preservation, and fluency. In principle, evaluations by human raters should be t
We take the first step towards multilingual style transfer by creating and releasing XFORMAL, a benchmark of multiple formal reformulations of informal text in Brazilian Portuguese, French, and Italian. Results on XFORMAL suggest that state-of-the-ar
Natural Language Generation (NLG) evaluation is a multifaceted task requiring assessment of multiple desirable criteria, e.g., fluency, coherency, coverage, relevance, adequacy, overall quality, etc. Across existing datasets for 6 NLG tasks, we obser
This paper studies zero-shot cross-lingual transfer of vision-language models. Specifically, we focus on multilingual text-to-video search and propose a Transformer-based model that learns contextual multilingual multimodal embeddings. Under a zero-s
Unsupervised style transfer models are mainly based on an inductive learning approach, which represents the style as embeddings, decoder parameters, or discriminator parameters and directly applies these general rules to the test cases. However, the