Dictionary-Guided Editing Networks for Paraphrase Generation解读

过程:输入->检索->编码->解码

解释:检索:输入一句话x,首先从PPDB中检索出M * 10 个释义对,并排序,记为x的本地字典;

编码:将所有的释义对编码为向量,单字转为字向量,多字将 每个字向量加和;论文认为会得到2×M个向量

解码过程:

首先,使用BiRNN的输出作为x的表征,并用standard attention获取句子信息,用来计算c’_t,它是原句隐藏状态的加权平均;

其次,计算释义字典侧信息的上下文向量c_t,它用来指导解码器(删除还是增加一个token);

 

再次,联结/级联h_t,c_t,c’_t,值为 ,其中h_t表示第t字的隐藏状态;


然后,利用softmax层,获取概率最大的句子y_t

最后,计算最小NLL

 

 

 

 

论文翻译:

1.方法论:

1)问题定义:有一个词汇或者短语字典(从PPDB中获取)

其中,o_i是原始字或者短语,p_io_i的字级或者短语级释义。有一个并行的数据集

其 中,(x_i,y_i) 是一个释义对。我们的目标是利用DP来学习一个释义生成器,以便于用y准确的释义一个新句子x.

 

 

 

 

模型概述:首先,对于原始句子x,我们先检索字级或者短语级的释义对集合

 

 

 

 

 

 

 

转载于:https://www.cnblogs.com/mj-selina/p/11153786.html

Generating long and semantic-coherent reports to describe medical images poses great challenges towards bridging visual and linguistic modalities, incorporating medical domain knowledge, and generating realistic and accurate descriptions. We propose a novel Knowledge-driven Encode, Retrieve, Paraphrase (KERP) approach which reconciles traditional knowledge- and retrieval-based methods with modern learning-based methods for accurate and robust medical report generation. Specifically, KERP decomposes medical reportgenerationintoexplicitmedicalabnormalitygraphlearning and subsequent natural language modeling. KERP first employs an Encode module that transforms visual features into a structured abnormality graph by incorporating prior medicalknowledge;thenaRetrievemodulethatretrievestext templates based on the detected abnormalities; and lastly, a Paraphrase module that rewrites the templates according to specificcases.ThecoreofKERPisaproposedgenericimplementation unit—Graph Transformer (GTR) that dynamically transforms high-level semantics between graph-structured data of multiple domains such as knowledge graphs, images andsequences.Experimentsshowthattheproposedapproach generates structured and robust reports supported with accurate abnormality description and explainable attentive regions, achieving the state-of-the-art results on two medical report benchmarks, with the best medical abnormality and disease classification accuracy and improved human evaluation performance.
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