Sentence Compression Using BERT and Graph Convolutional Networks

Abstract

Sentence compression is a natural language-processing task that produces a short paraphrase of an input sentence by deleting words from the input sentence while ensuring grammatical correctness and preserving meaningful core information. This study introduces a graph convolutional network (GCN) into a sentence compression task to encode syntactic information, such as dependency trees. As we upgrade the GCN to activate a directed edge, the compression model with the GCN layers can distinguish between parent and child nodes in a dependency tree when aggregating adjacent nodes. Furthermore, by increasing the number of GCN layers, the model can gradually collect high-order information of a dependency tree when propagating node information through the layers. We implement a sentence compression model for Korean and English, respectively. This model consists of three components: pre-trained BERT model, GCN layers, and a scoring layer. The scoring layer can determine whether a word should remain in a compressed sentence by relying on the word vector containing contextual and syntactic information encoded by BERT and GCN layers. To train and evaluate the proposed model, we used the Google sentence compression dataset for English and a Korean sentence compression corpus containing about 140,000 sentence pairs for Korean. The experimental results demonstrate that the proposed model achieves state-of-the-art performance for English. To the best of our knowledge, this sentence compression model based on the deep learning model trained with a large-scale corpus is the first attempt for Korean.

Keywords

• dependency tree
• graph convolutional network
• graph neural networks
• pre-trained model
• sentence compression