Semantic Relation Classification——via Convolution Neural Network: Difference between revisions

From statwiki
Jump to navigation Jump to search
No edit summary
Line 13: Line 13:


== Previous Work ==
== Previous Work ==
SemEval 2010 Task 8(Hendrickx et al., 2010) explored the classification of natural language relations and studied the 9 relations between word pairs. However, it is not specially for scientific text analysis. Xu et al. (2015a) and Santos et al. (2015) , both of them applied CNN with negative sampling to finish task7. The 2017 SemEval Task 10 also featured relation extraction within scientific publications.
SemEval 2010 Task 8(Hendrickx et al., 2010) explored the classification of natural language relations and studied the 9 relations between word pairs. However, it is not designed for scientific text analysis. Xu et al. (2015a) and Santos et al. (2015) , both of them applied CNN with negative sampling to finish task7. The 2017 SemEval Task 10 also featured relation extraction within scientific publications.


== Algorithm ==
== Algorithm ==
Line 19: Line 19:
[[File:CNN.png|800px]]
[[File:CNN.png|800px]]


This is the architecture of the CNN. We first transform a sentence via Feature embeddings. Basically we transform each sentence into continuous word embeddings:
This is the architecture of CNN. We first transform a sentence via Feature embeddings. Basically, we transform each sentence into continuous word embeddings:


$$
$$
Line 31: Line 31:


In the word embeddings, we got a vocabulary ‘V’, and we will make an embedding word matrix based on the position of the word in the vocabulary. This matrix is trainable and needs to be initialized by pre-trained embedding vectors.
In the word embeddings, we got a vocabulary ‘V’, and we will make an embedding word matrix based on the position of the word in the vocabulary. This matrix is trainable and needs to be initialized by pre-trained embedding vectors.
In the word position embeddings, we first need to input some words named ‘entities’ and they are the key for the machine to determinate sentence’s relation. During this process, if we have two entities, we will used the relative position of them in the sentence to make the
In the word position embeddings, we first need to input some words named ‘entities’ and they are the key for the machine to determine the sentence’s relation. During this process, if we have two entities, we will use the relative position of them in the sentence to make the
embeddings. We will output two vectors and one of them keep track of the first entity relative position in the sentence ( we will make the entity recorded as 0, the former word recorded as -1 and the next one 1, etc. ). And the same procedure for the second entity. Finally we will get two vectors concatenated as the position embedding.
embeddings. We will output two vectors and one of them keeps track of the first entity relative position in the sentence ( we will make the entity recorded as 0, the former word recorded as -1 and the next one 1, etc. ). And the same procedure for the second entity. Finally, we will get two vectors concatenated as the position embedding.




After the embeddings, the model will transform the embedded sentence to a fix-sized representation of the whole sentence via the convolution layer, finally after the max pooling to reduce the dimension of the output of the layers, we will get a score for each relation class via a linear transformation.
After the embeddings, the model will transform the embedded sentence to a fix-sized representation of the whole sentence via the convolution layer, finally after the max-pooling to reduce the dimension of the output of the layers, we will get a score for each relation class via a linear transformation.




Line 77: Line 77:
size and it improves the equality between classes to get better predictions.
size and it improves the equality between classes to get better predictions.


2. Reversal Indicate Features. It added binary feature.
2. Reversal Indicate Features. It added a binary feature.


3. Custom ACL Embeddings. It embedded word vector to an ACL-specific
3. Custom ACL Embeddings. It embedded word vector to an ACL-specific
corps.
corps.


4. Context words. Within the sentence, it varies size on a context window
4. Context words. Within the sentence, it varies in size on a context window
around the entity-enclosed text.
around the entity-enclosed text.


Line 89: Line 89:


These modifications performances well on the training data and they are shown
These modifications performances well on the training data and they are shown
in the table 3.
in table 3.


                                                                                   [[File:table3.PNG]]
                                                                                   [[File:table3.PNG]]
Line 107: Line 107:


The best submission for training set 1.1 is the third submission which did not
The best submission for training set 1.1 is the third submission which did not
use the cross validation as the test set. Instead, it runs a constant number of
use the cross-validation as the test set. Instead, it runs a constant number of
training epochs and based on the training data it can be chosen by cross validation. The best submission for training set 1.2 is the first submission which
training epochs and based on the training data it can be chosen by cross-validation. The best submission for the training set 1.2 is the first submission which
extracted 10% of the training data as validation accuracy on the test set predictions.
extracted 10% of the training data as validation accuracy on the test set predictions.
All in all, early stop cannot always based on the accuracy of the validation set
All in all, earlystoping cannot always based on the accuracy of the validation set
since it cannot guarantee to get better performance on the real test set. Thus,
since it cannot guarantee to get better performance on the real test set. Thus,
we have to try new approaches and combine them together to see the prediction
we have to try new approaches and combine them together to see the prediction
Line 117: Line 117:


== Conclusions ==
== Conclusions ==
Throughout the process, linear classifiers, sequential random forest, LSTM and CNN models are tested. Variations are applied to the models. Among all variations, vanilla CNN with negative sampling and ACL-embedding has significant better performance than all others. Attention based pooling, up-sampling and data augmentation are also tested, but they barely perform positive incresement on the behaviour.
Throughout the process, linear classifiers, sequential random forest, LSTM, and CNN models are tested. Variations are applied to the models. Among all variations, vanilla CNN with negative sampling and ACL-embedding has significant better performance than all others. Attention based pooling, up-sampling and data augmentation are also tested, but they barely perform positive increment on the behavior.


== Critiques ==  
== Critiques ==  

Revision as of 10:34, 25 November 2020


Presented by

Rui Gong, Xinqi Ling, Di Ma,Xuetong Wang

Introduction

One of the emerging trends of natural language technologies is their use for the humanities and sciences (Gbor et al., 2018). SemEval 2018 Task 7 mainly solves the problem of relation extraction and classification of two entities in the same sentence into 6 potential relations. The 6 relations are USAGE, RESULT, MODEL-FEATURE,PART WHOLE, TOPIC, and COMPARE.

Data comes from 350 scientific paper abstracts, which have 1228 and 1248 annotated sentences for two tasks. For each data, an example sentence was chosen with its right and left sentences, as well as an indicator showing whether the relation is reserved, then a prediction is made.

Three models were used for the prediction: Linear Classifiers, Long Short-Term Memory(LSTM), and Convolutional Neural Networks (CNN). In the end, the CNN model category performed best, so the article specifically submitted the final submission for this model. By using the learned custom word embedding function, the research team added a variant of negative sampling, thereby improving performance and surpassing ordinary CNN.

Previous Work

SemEval 2010 Task 8(Hendrickx et al., 2010) explored the classification of natural language relations and studied the 9 relations between word pairs. However, it is not designed for scientific text analysis. Xu et al. (2015a) and Santos et al. (2015) , both of them applied CNN with negative sampling to finish task7. The 2017 SemEval Task 10 also featured relation extraction within scientific publications.

Algorithm

This is the architecture of CNN. We first transform a sentence via Feature embeddings. Basically, we transform each sentence into continuous word embeddings:

$$ (e^{w_i}) $$

And word position embeddings: $$ (e^{wp_i}): e_i = [e^{w_i}, e^{wp_i}] $$

In the word embeddings, we got a vocabulary ‘V’, and we will make an embedding word matrix based on the position of the word in the vocabulary. This matrix is trainable and needs to be initialized by pre-trained embedding vectors. In the word position embeddings, we first need to input some words named ‘entities’ and they are the key for the machine to determine the sentence’s relation. During this process, if we have two entities, we will use the relative position of them in the sentence to make the embeddings. We will output two vectors and one of them keeps track of the first entity relative position in the sentence ( we will make the entity recorded as 0, the former word recorded as -1 and the next one 1, etc. ). And the same procedure for the second entity. Finally, we will get two vectors concatenated as the position embedding.


After the embeddings, the model will transform the embedded sentence to a fix-sized representation of the whole sentence via the convolution layer, finally after the max-pooling to reduce the dimension of the output of the layers, we will get a score for each relation class via a linear transformation.


After featurizing all words in the sentence. The sentence of length N can be expressed as a vector of length [math]\displaystyle{ N }[/math], which looks like $$e=[e_{1},e_{2},\ldots,e_{N}]$$ and each entry represents a token of the word. Also, to apply convolutional neural network, the subsets of features $$e_{i:i+j}=[e_{i},e_{i+1},\ldots,e_{i+j}]$$ is given to a weight matrix [math]\displaystyle{ W\in\mathbb{R}^{(d^{w}+2d^{wp})\times k} }[/math] to produce a new feature, defiend as $$c_{i}=\text{tanh}(W\cdot e_{i:i+k-1}+bias)$$ This process is applied to all subsets of features with length [math]\displaystyle{ k }[/math] starting from the first one. Then a mapped feature factor $$c=[c_{1},c_{2},\ldots,c_{N-k+1}]$$ is produced.

The max pooling operation is used, the [math]\displaystyle{ \hat{c}=max\{c\} }[/math] was picked. With different weight filter, different mapped feature vectors can be obtained. Finally, the original sentence [math]\displaystyle{ e }[/math] can be converted into a new representation [math]\displaystyle{ r_{x} }[/math] with a fixed length. For example, if there are 5 filters, then there are 5 features ([math]\displaystyle{ \hat{c} }[/math]) picked to create [math]\displaystyle{ r_{x} }[/math] for each [math]\displaystyle{ x }[/math].

Then, the score vector $$s(x)=W^{classes}r_{x}$$ is obtained which represented the score for each class, given [math]\displaystyle{ x }[/math]'s entities' relation will be classified as the one with the highest score. The [math]\displaystyle{ W^{classes} }[/math] here is the model being trained.

To improve the performance, “Negative Sampling" was used. Given the trained data point [math]\displaystyle{ \tilde{x} }[/math], and its correct class [math]\displaystyle{ \tilde{y} }[/math]. Let [math]\displaystyle{ I=Y\setminus\{\tilde{y}\} }[/math] represent the incorrect labels for [math]\displaystyle{ x }[/math]. Basically, the distance between the correct score and the positive margin, and the negative distance (negative margin plus the second largest score) should be minimized. So the loss function is $$L=\log(1+e^{\gamma(m^{+}-s(x)_{y})})+\log(1+e^{\gamma(m^{-}-\mathtt{max}_{y'\in I}(s(x)_{y'}))})$$ with margins [math]\displaystyle{ m_{+} }[/math], [math]\displaystyle{ m_{-} }[/math], and penalty scale factor [math]\displaystyle{ \gamma }[/math]. The whole training is based on ACL anthology corpus and there are 25,938 papers with 136,772,370 tokens in total, and 49,600 of them are unique.

Results

In machine learning, the most important part is to tune the hyper-parameters. Unlike traditional hyper-parameter optimization, there are some modifications to the model in order to increase performance on the test set. There are 5 modifications that we can apply:

1. Merged Training Sets. It combined two training sets to increase the data set size and it improves the equality between classes to get better predictions.

2. Reversal Indicate Features. It added a binary feature.

3. Custom ACL Embeddings. It embedded word vector to an ACL-specific corps.

4. Context words. Within the sentence, it varies in size on a context window around the entity-enclosed text.

5. Ensembling. It used different early stop and random initializations to improve the predictions.

These modifications performances well on the training data and they are shown in table 3.

                                                                                 


As we can see the best choice for this model is ensembling. Because the random initialization made the data more nature and avoided the overfit. During the training process, there are some methods such that they can only increases the score on the cross validation test sets but hurt the performance on the overall macro-F1 score. Thus, these methods were eventually ruled out.


                                                                                 

There are six submissions in total. Three for each training set and the result is shown in figure 2.

The best submission for training set 1.1 is the third submission which did not use the cross-validation as the test set. Instead, it runs a constant number of training epochs and based on the training data it can be chosen by cross-validation. The best submission for the training set 1.2 is the first submission which extracted 10% of the training data as validation accuracy on the test set predictions. All in all, earlystoping cannot always based on the accuracy of the validation set since it cannot guarantee to get better performance on the real test set. Thus, we have to try new approaches and combine them together to see the prediction results. Also, doing stratification will certainly to improve the performance on the test data.

Conclusions

Throughout the process, linear classifiers, sequential random forest, LSTM, and CNN models are tested. Variations are applied to the models. Among all variations, vanilla CNN with negative sampling and ACL-embedding has significant better performance than all others. Attention based pooling, up-sampling and data augmentation are also tested, but they barely perform positive increment on the behavior.

Critiques

- Applying this in news apps might be beneficial to improve readability by highlighting specific important sections.

References

Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.

DragomirR. Radev, Pradeep Muthukrishnan, Vahed Qazvinian, and Amjad Abu-Jbara. 2013. The ACL anthology network corpus. Language Resources and Evaluation, pages 1–26.

Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013a. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781.

Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013b. Distributed representations of words and phrases and their compositionality. In Advances in neural information processing systems, pages 3111–3119.

Kata Gbor, Davide Buscaldi, Anne-Kathrin Schumann, Behrang QasemiZadeh, Hafa Zargayouna, and Thierry Charnois. 2018. Semeval-2018 task 7:Semantic relation extraction and classification in scientific papers. In Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval2018), New Orleans, LA, USA, June 2018.