SCROLLS：长语言序列上的标准化CompaRison
SCROLLS: Standardized CompaRison Over Long Language Sequences
摘要：
NLP基准主要集中在短文本上，例如句子和段落，即使长文本包含大量的自然自然语言。我们介绍了卷轴，一套任务，需要推理长文本。我们检查现有的长文本数据集，并精心挑选文本自然较长的数据集，同时优先考虑涉及在输入中合成信息的任务。SCROLLS包含摘要、问答和自然语言推理任务，涵盖多个领域，包括文学、科学、商业和娱乐。初始基线，包括Longformer编码器-解码器，表明SCROLLS有足够的改进空间。我们以统一的文本到文本格式提供所有数据集，并提供实时排行榜，以促进对模型架构和预训练方法的研究。
英文摘要：
NLP benchmarks have largely focused on short texts, such as sentences and paragraphs, even though long texts comprise a considerable amount of natural language in the wild. We introduce SCROLLS, a suite of tasks that require reasoning over long texts. We examine existing long-text datasets, and handpick ones where the text is naturally long, while prioritizing tasks that involve synthesizing information across the input. SCROLLS contains summarization, question answering, and natural language inference tasks, covering multiple domains, including literature, science, business, and entertainment. Initial baselines, including Longformer Encoder-Decoder, indicate that there is ample room for improvement on SCROLLS. We make all datasets available in a unified text-to-text format and host a live leaderboard to facilitate research on model architecture and pretraining methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
