TurkuNLP/finbenchv2-squad_v2-fi-mt

这是一个芬兰语的SQuAD问题回答数据集，用于Finbench版本2。它是基于英语SQuAD2.0数据集的DeepL机器翻译版本，包含了SQuAD1.1中的100,000个问题和超过50,000个由众包工作者编写的对抗性无答案问题，这些问题看起来与有答案的问题相似。为了在SQuAD2.0上表现良好，系统必须不仅要能在可能的情况下回答问题，还要能够确定当段落不支持答案时不去回答。

This is a Finnish SQuAD question answering dataset used in Finbench version 2. It is a DeepL-based machine translation of the English SQuAD2.0 dataset, which combines the 100,000 questions in SQuAD1.1 with over 50,000 unanswerable questions written adversarially by crowdworkers to look similar to answerable ones. To do well on SQuAD2.0, systems must not only answer questions when possible, but also determine when no answer is supported by the paragraph and abstain from answering.