arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1609.09580cs.CL
收藏

高维连续意义空间中的指称不确定性与词汇学习

Referential Uncertainty and Word Learning in High-dimensional, Continuous Meaning Spaces

Sony Computer Science Laboratories Inc.(索尼计算机科学实验室公司);Vrije Universiteit Brussel(布鲁塞尔自由大学)

Michael Spranger, Katrien Beuls

摘要:

本文从指称不确定性的角度探讨了高维意义空间中的词汇学习。我们研究了各种最先进的机器学习算法,并讨论了缩放,表示和意义空间结构的影响。我们证明了当前的机器学习技术成功地处理了高维意义空间。特别是,我们发现,指数增加的维度线性影响学习者的表现,从词的敏感性的参考不确定性没有影响。

英文摘要:

This paper discusses lexicon word learning in high-dimensional meaning spaces from the viewpoint of referential uncertainty. We investigate various state-of-the-art Machine Learning algorithms and discuss the impact of scaling, representation and meaning space structure. We demonstrate that current Machine Learning techniques successfully deal with high-dimensional meaning spaces. In particular, we show that exponentially increasing dimensions linearly impact learner performance and that referential uncertainty from word sensitivity has no impact.

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。

↑