arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1606.07902cs.CL
收藏

词嵌入表示的内在子空间计算

Intrinsic Subspace Evaluation of Word Embedding Representations

Center for Information and Language Processing(信息与语言处理中心);University of Munich(慕尼黑大学)

Yadollah Yaghoobzadeh, Hinrich Schütze

摘要:

我们介绍了一种新的方法,字表征的内在评价。具体来说,我们确定了四个基本标准的基础上的自然语言的特点,造成困难的NLP系统,并开发测试,直接显示表示是否包含必要的子空间,以满足这些标准。目前的内在评价大多基于词的整体相似性或全空间相似性,因此将向量表示视为点。我们展示了这些基于点的内在评价的局限性。我们应用我们的评估方法的计数向量模型和几个神经网络模型的比较,并证明这些模型的重要属性。

英文摘要:

We introduce a new methodology for intrinsic evaluation of word representations. Specifically, we identify four fundamental criteria based on the characteristics of natural language that pose difficulties to NLP systems; and develop tests that directly show whether or not representations contain the subspaces necessary to satisfy these criteria. Current intrinsic evaluations are mostly based on the overall similarity or full-space similarity of words and thus view vector representations as points. We show the limits of these point-based intrinsic evaluations. We apply our evaluation methodology to the comparison of a count vector model and several neural network models and demonstrate important properties of these models.

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。

↑