人工智能培训

搜索

机器学习论文:使用序贯神经网络学习名词案例(Learning Noun Cases Using Sequential Neural Networks)

[复制链接]
rrrrrrr 发表于 2018-10-11 09:04:42 | 显示全部楼层 |阅读模式
rrrrrrr 2018-10-11 09:04:42 203 0 显示全部楼层
机器学习论文:使用序贯神经网络学习名词案例(Learning Noun Cases Using Sequential Neural Networks)形态上的变形,旨在用于表示数字,案例和性别的名词,是自然语言处理(NLP)中的一项重要任务。本研究提案旨在解决Recurrent NeuralNetworks(RNNs)在学习拒绝名词方面的有效程度案例。鉴于数据稀疏性在处理形态丰富的语言时的挑战,以及这些语言中句子结构的灵活性,我们认为模型形态依赖性可以提高神经网络模型的性能。建议进行各种实验以理解可解释的特征,这些特征可能导致在跨语言任务上更好地概括所学习的模型。
Morphological declension, which aims to inflect nouns to indicate number,case and gender, is an important task in natural language processing (NLP).This research proposal seeks to address the degree to which Recurrent NeuralNetworks (RNNs) are efficient in learning to decline nouncases.Given thechallenge of data sparsity in processing morphologically rich languages andalso, the flexibility of sentence structures in such languages, we believe thatmodeling morphological dependencies can improve the performance of neuralnetwork models.It is suggested to carry out various experiments to understandthe interpretable features that may lead to a better generalization of thelearned models on cross-lingual tasks.机器学习论文:使用序贯神经网络学习名词案例(Learning Noun Cases Using Sequential Neural Networks) W96mzRrh9b96m19q.jpg
URL地址:https://arxiv.org/abs/1810.03996     ----pdf下载地址:https://arxiv.org/pdf/1810.03996    ----机器学习论文:使用序贯神经网络学习名词案例(Learning Noun Cases Using Sequential Neural Networks)
回复

使用道具 举报

您需要登录后才可以回帖 登录 | 立即注册

本版积分规则 返回列表 发新帖

rrrrrrr当前离线
新手上路

查看:203 | 回复:0

快速回复 返回顶部 返回列表