arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.07218cs.CL
收藏

CA-EHN:E-HowNet的常识类比

CA-EHN: Commonsense Analogy from E-HowNet

Academia Sinica(中央研究院)

Peng-Hsuan Li, Tsan-Yu Yang, Wei-Yun Ma

摘要:

嵌入常识知识对于端到端模型在训练语料库之外推广推理至关重要。然而,现有的单词类比数据集往往是手工制作的,涉及数百个单词的排列,只有几十个预定义的关系,主要是形态关系和命名实体。在这项工作中,我们利用E-HowNet,本体,注释88 K中文单词与他们的结构化意义定义和英语翻译的常识知识模型到单词级的类比推理。我们提出了CA-EHN,第一个常识词类比数据集,包含90,505个类比,涵盖5,656个词和763个关系。实验表明,CA-EHN是一个很好的指标,可以很好地显示单词表示嵌入常识知识的程度。该数据集可在https://github.com/ckiplab/CA-EHN上公开获得。

英文摘要:

Embedding commonsense knowledge is crucial for end-to-end models to generalize inference beyond training corpora. However, existing word analogy datasets have tended to be handcrafted, involving permutations of hundreds of words with only dozens of pre-defined relations, mostly morphological relations and named entities. In this work, we model commonsense knowledge down to word-level analogical reasoning by leveraging E-HowNet, an ontology that annotates 88K Chinese words with their structured sense definitions and English translations. We present CA-EHN, the first commonsense word analogy dataset containing 90,505 analogies covering 5,656 words and 763 relations. Experiments show that CA-EHN stands out as a great indicator of how well word representations embed commonsense knowledge. The dataset is publicly available at https://github.com/ckiplab/CA-EHN.

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。

↑