English Learning from research paper

英语句子学习

[sentence.01]

The task of item recommendation is modeled by a three-way tensor over user, item and feature, to describe users’ preferences on individual items’ features, constructed by feature-level sentiment analysis in opinionated review content.

物品推荐任务通过一个三元张量进行建模,该三元张量由用户、物品和特征组成 (user, item, feature),通过观点评论内容的特征级情感分析来构建,用于描述用户对单个物品特征的偏好。


等价为
The task of item recommendation is modeled by a three-way tensor over user, item and feature.
by a three-way tensor to describe users’ preferences on individual items’ features.
a three-way tensor is constructed by feature-level sentiment analysis in opinionated review content.

文本内容理解的依据
The companion task of opinionated content analysis is modeled by another two three-way tensors, one over user, feature, opinionated phrase, and another over item, feature, opinionated phrase, both of which are constructed from user-generated review content. Among these two tensors, the first one specifies what kind of text descriptions a user usually provides to depict a particular feature of a given item, and the second describes what kind of opinionated comments an item often receives on its features.

由这段文字可以知道:to describe… 和 constructed by… 都是对 two three-way tensors 进行说明的。

[sentence.02]

We describe a novel, multi-task recommendation model, which jointly learns to perform rating prediction and recommendation explanation by combining matrix factorization, for rating prediction, and adversarial sequence to sequence learning for explanation generation.

提出了一种新的多任务推荐模型,该模型通过结合矩阵分解 (用于评分预测) 和对抗序列到序列学习 (用于生成解释) 方法,实现评分预测和生成解释。


等价为

  • 0
    点赞
  • 1
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值