arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1804.08207cs.CL
收藏

收集不同的自然语言推理问题用于句子表示评估

Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation

Johns Hopkins University(约翰斯·霍普金斯大学);BITS Pilani, Goa Campus(贝拉理工学院皮拉尼分校果阿校区);Brown University(布朗大学);University of Rochester(罗切斯特大学)

Adam Poliak, Aparajita Haldar, Rachel Rudinger, J. Edward Hu, Ellie Pavlick, Aaron Steven White, Benjamin Van Durme

摘要:

我们提出了一个大规模的收集不同的自然语言推理(NLI)数据集,帮助提供洞察如何以及一个句子表示捕捉不同类型的推理。收集结果从重铸13个现有的数据集从7个语义现象到一个共同的NLI结构,导致超过50万个标记的上下文假设对。我们将我们的集合称为DNC:多样自然语言推理集合。DNC可在https://www.decomp.net上在线获得,并将随着时间的推移而增长,因为其他资源将从新的来源重新铸造和添加。

英文摘要:

We present a large-scale collection of diverse natural language inference (NLI) datasets that help provide insight into how well a sentence representation captures distinct types of reasoning. The collection results from recasting 13 existing datasets from 7 semantic phenomena into a common NLI structure, resulting in over half a million labeled context-hypothesis pairs in total. We refer to our collection as the DNC: Diverse Natural Language Inference Collection. The DNC is available online at https://www.decomp.net, and will grow over time as additional resources are recast and added from novel sources.

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。

↑