ParsiNLU: A Suite of Language Understanding Challenges for Persian

Abstract

Despite the progress made in recent years in addressing natural language understanding (NLU) challenges, the majority of this progress remains to be concentrated on resource-rich languages like English. This work focuses on Persian language, one of the widely spoken languages in the world, and yet there are few NLU datasets available for this rich language. The availability of high-quality evaluation datasets is a necessity for reliable assessment of the progress on different NLU tasks and domains. We introduce ParsiNLU, the first benchmark in Persian language that includes a range of high-level tasks -- Reading Comprehension, Textual Entailment, etc. These datasets are collected in a multitude of ways, often involving manual annotations by native speakers. This results in over 14.5$k$ new instances across 6 distinct NLU tasks. Besides, we present the first results on state-of-the-art monolingual and multi-lingual pre-trained language-models on this benchmark and compare them with human performance, which provides valuable insights into our ability to tackle natural language understanding challenges in Persian. We hope ParsiNLU fosters further research and advances in Persian language understanding.

arXiv commentTo appear on Transactions of the Association for Computational Linguistics (TACL), 2021

References in corpus (18)

• Language Models are Few-Shot Learners
• On the Cross-lingual Transferability of Monolingual Representations
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization
• XNLI: Evaluating Cross-lingual Sentence Representations
• Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
• XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
• CLUE: A Chinese Language Understanding Evaluation Benchmark
• RussianSuperGLUE: A Russian Language Understanding Evaluation Benchmark
• KorQuAD1.0: Korean QA Dataset for Machine Reading Comprehension
• SentiPers: A Sentiment Analysis Corpus for Persian
• TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages
• From 'F' to 'A' on the N.Y. Regents Science Exams: An Overview of the Aristo Project
• FarsTail: A Persian Natural Language Inference Dataset
• DeepSentiPers: Novel Deep Learning Models Trained Over Proposed Augmented Persian Sentiment Corpus
• Pars-ABSA: an Aspect-based Sentiment Analysis dataset for Persian
• MIZAN: A Large Persian-English Parallel Corpus
• El Departamento de Nosotros: How Machine Translated Corpora Affects Language Models in MRC Tasks

Cited by in corpus (4)

• KLUE: Korean Language Understanding Evaluation
• AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing
• FarsTail: A Persian Natural Language Inference Dataset
• Investigating Transfer Learning in Multilingual Pre-trained Language Models through Chinese Natural Language Inference