Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

CoRR(J)-2017-A Survey of Deep Learning Methods for Relation Extraction #10

Open
BrambleXu opened this issue Feb 13, 2019 · 0 comments
Open
Assignees
Labels
RE(T) Relation Extraction Task Survey Survey/Review

Comments

@BrambleXu
Copy link
Owner

BrambleXu commented Feb 13, 2019

总结

数据

  1. 监督式训练
  • ACE 2005
  • SemEval-2010 Task 8 dataset
  1. Distant supervision(远程监控)
  • aligning Freebase relations with the New York Times corpus

Basic Concepts

  • Word Embeddings
  • Positional Embeddings: The idea is that words closer to the target entities usually contain more useful information regarding the relation class. 离实体越近的单词,包含关于relation的信息也多。所以通过embedding来获取这些信息。
  • Convolutional Neural Networks: capture ngram level features

Supervised learning with CNNs

早期DL在RE方面的研究就是把RE当做了一个多分类问题。

  • 4.1 Simple CNN model (Liu et al., 2013)
    • 没有使用word embedidng。在ACE上币当时的SOTA kernel-based模型效果好了9个百分点。
  • 4.2 CNN model with max-pooling (Zeng et al., 2014)
    • 使用了word embedding,以及positional mebdding,也用了lexical level features。最主要的贡献是在卷积层之后使用了max-pooling layer。
  • 4.3 CNN with multi-sized window kernels (Nguyen and Grishman, 2015)
    • 完全去除了lexical level features。只让CNN自己去学特征。基本和上面4.2的一样,只不过使用了不同size的window来捕捉不同的n-gram情报

Multi-instance learning models with distant supervision

把问题变为Multi-instance learning问题,这样我们可以通过远程监督来构建更大的训练集。Multi-instance learning是distant supervision的一种,含义是一个label有一群instance,而不是单单的一个instance。

在RE这个问题上,每个entity pair定义一个bag,这个bag包含涉及到entity pair的所有句子。然后我们把一个relation label标记给整个bag,而不是单单一个instance。

  • 5.1 Piecewise Convolutional Neural Networks (Zeng et al., 2015)

    • 构建一个神经网络模型,从distant supervision data中构建一个relation extractor。网络模型和上面4.3,4.2的差不多,但是一个最大的贡献是使用了piecewise max-pooling across the sentence. 之前4.3的模型是在整个句子上做了max-pooling,这样会浪费大量信息。因为有两个entity,所以一个句子可以分为3个segment,然后分别在这3个segment上做max-pooling,这样能保留一些有用的信息。
    • 但是这个模型有缺点。根据损失函数的设计,训练和预测的时候只是从bag里调出一个最能代表整个bag的document,没有好好把整个distant supervision data利用起来。
    • 效果方面PCNN确实比CNN好
  • 5.2 Selective Attention over Instances (Lin et al., 2016)

    • 为了解决5.1中只使用最相关document的问题,这篇论文通过attention机制对一个bag的所有document进行处理。Then the final vector representation for the bag of sentences is found by taking an attention-weighted average of all the sentence vectors (r i j , j = 1, 2...q i ) in the bag.
  • 效果币PCNN好

  • 5.3 Multi-instance Multi-label CNNs (Jiang et al., 2016)

    • 解决了5.1的信息丢失问题 by using a crossdocument max-pooling layer. 对bag中的每一个句子做一个向量表示。Then the final vector representation for the bag of sentences is found by taking a dimension wise max of the sentence vectors (r i j , j = 1, 2...q i ). 最终的bag vector是针对每个维度,从所有的句子向量的相同维度中,找出数字最大的那个。
    • 还解决了多标签的问题。一个entity pair有多个relaiton。具体做法是把最后一层的softmax换位sigmoid。

Results

深度模型普遍比不深的好。attention + PCNN是效果最好的。奇怪的是没有LSTM在RE方面的工作。

下一篇论文

Relation Extraction : A Survey

@BrambleXu BrambleXu added the RE(T) Relation Extraction Task label Feb 13, 2019
@BrambleXu BrambleXu changed the title A Survey of Deep Learning Methods for Relation Extraction-2017 A Survey of Deep Learning Methods for Relation Extraction (2017) Feb 21, 2019
@BrambleXu BrambleXu self-assigned this Feb 22, 2019
@BrambleXu BrambleXu added the Survey Survey/Review label Mar 18, 2019
@BrambleXu BrambleXu changed the title A Survey of Deep Learning Methods for Relation Extraction (2017) CoRR(J)-2017-A Survey of Deep Learning Methods for Relation Extraction Apr 10, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
RE(T) Relation Extraction Task Survey Survey/Review
Projects
None yet
Development

No branches or pull requests

1 participant