DOLPHIN: A Challenging and Diverse Benchmark for Arabic NLG
Document Type
Conference Proceeding
Publication Title
Findings of the Association for Computational Linguistics: EMNLP 2023
Abstract
We present Dolphin, a novel benchmark that addresses the need for a natural language generation (NLG) evaluation framework dedicated to the wide collection of Arabic languages and varieties. The proposed benchmark encompasses a broad range of 13 different NLG tasks, including dialogue generation, question answering, machine translation, summarization, among others. Dolphin comprises a substantial corpus of 40 diverse and representative public datasets across 50 test splits, carefully curated to reflect real-world scenarios and the linguistic richness of Arabic. It sets a new standard for evaluating the performance and generalization capabilities of Arabic and multilingual models, promising to enable researchers to push the boundaries of current methodologies. We provide an extensive analysis of Dolphin, highlighting its diversity and identifying gaps in current Arabic NLG research. We also offer a public leaderboard that is both interactive and modular and evaluate several models on our benchmark, allowing us to set strong baselines against which researchers can compare.
First Page
1404
Last Page
1422
Publication Date
1-1-2023
Recommended Citation
E. Nagoudi et al., "DOLPHIN: A Challenging and Diverse Benchmark for Arabic NLG," Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 1404 - 1422, Jan 2023.