Advertisement

(2015ACL) Classifying Relations by Ranking with Convolutional Neural Networks

阅读量:

论文: https://www.aclweb.org/anthology/P15-1061 或者 https://pan.baidu.com/s/1qFGhrMIO31s0pVvv0eJkMQ
机构: IBM
模型: CR-CNN

数据: SemEval2010-Task8
结果: F1值,84.1%
备注: 只利用了预训练好的词向量表示

输入: 一个包含两个标注实体的句子,例如 The [car] left the [plant]
输出: 一个向量,各维度代表各个关系的概率
在这里插入图片描述
过程:

Word Embeddings
通用的获取词向量流程:
预先训练好的embedding matrix 为: W^{wrd} \in \mathbb{R}^{d_w \times |V|}d_w为词向量的维度,|V|为单词总数
列向量W^{wrd}_i \in \mathbb{R}^{d_w } 即为 第 i 个词对应的词向量

w得到其词向量r_w的公式为:r_w=W^{wrd}v^wv^w是一个w维度为1,其余维度为0的总维度为|V|的向量

Word Position Embeddings

(2014COLING) Relation Classification via Convolutional Deep Neural Network 那篇论文中PF的获取方式

wpe^w = [wp_1, wp_2]wp_1wp_2d_{wpe}维的向量

于是,句子x转化为向量表示emb_x= { [r^{w_1},wpe^{w_1}], [r^{w_2},wpe^{w_2}],…,[r^{w_N},wpe^{w_N}]}
(备注:实例图中每个词的维度为d_w,没有考虑position embeddings)

Sentence Representation

利用CNN提取句子x的特征向量r_x

Class embeddings and Scoring [论文创新点]
普通方式为:将特征向量输入softmax classifier得到最终结果
本文的创新点为:

模型为每种关系学习一个向量表示
W^{classes}为关系对应的embedding matrix,每一列为一种关系对应的向量表示
关系c的向量表示即为[W^{classes}]_c,维度与句子x的特征向量r_x相同
于是,两向量相乘 r_x^T [W^{classes}]_c,可以得到一个值
至此,模型为句子x、关系c学到一个值:s_\theta(x)_c=r_x^T [W^{classes}]_c
其中,\theta表示模型的所有参数

训练过程中,一个句子x对应一个正例y^+和一个负例c^-
y^+是句子真正对应的关系类别,c^-则为其它关系类别中的一个
正例对应的值为s_\theta(x)_{y^+},负例对应的值为s_\theta(x)_{c^-}
损失函数为L=log(1+exp(\gamma(m^+-s_\theta(x)_{y^+})))+log(1+exp(\gamma(m^-+s_\theta(x)_{c^-})))
m^+m^-为margin值,\gamma为放大系数
训练过程中,使s_\theta(x)_{y^+}逐渐大于m^+s_\theta(x)_{c^-}逐渐小于m^-

原文:

复制代码
* The proposed network learns a distributed vector representation for each relation class.
* Given an input text segment, the network uses a convolutional layer to produce a distributed vector representation of the text and compares it to the class representations in order to produce a score for each class.
* We propose a new pairwise ranking loss function that makes it easy to reduce the impact of artificial classes.

BibTeX:

复制代码
    @inproceedings{dos-santos-etal-2015-classifying,
    title = "Classifying Relations by Ranking with Convolutional Neural Networks",
    author = "dos Santos, C{\'\i}cero  and
      Xiang, Bing  and
      Zhou, Bowen",
    booktitle = "Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = jul,
    year = "2015",
    address = "Beijing, China",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/P15-1061",
    doi = "10.3115/v1/P15-1061",
    pages = "626--634",
    }
    
    
    
![](https://ad.itadn.com/c/weblog/blog-img/images/2025-08-17/bE0Ykf12tTmOCzngouj98x75J4as.png)

全部评论 (0)

还没有任何评论哟~