DRCD: a Chinese Machine Reading Comprehension Dataset
This provides a standard dataset for Chinese MRC, useful for researchers in natural language processing, but it is incremental as it adapts existing MRC approaches to a new language domain.
The authors introduced DRCD, a traditional Chinese machine reading comprehension dataset with 10,014 paragraphs and over 30,000 questions, and built a baseline model achieving an F1 score of 89.59%, compared to human performance of 93.30%.
In this paper, we introduce DRCD (Delta Reading Comprehension Dataset), an open domain traditional Chinese machine reading comprehension (MRC) dataset. This dataset aimed to be a standard Chinese machine reading comprehension dataset, which can be a source dataset in transfer learning. The dataset contains 10,014 paragraphs from 2,108 Wikipedia articles and 30,000+ questions generated by annotators. We build a baseline model that achieves an F1 score of 89.59%. F1 score of Human performance is 93.30%.