Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks

By Ningyu Zhang, Shumin Deng, Zhanlin Sun, Guanying Wang, Xi Chen, Wei Zhang, Huajun Chen. 2019

216 citations recorded by the source corpus.

We propose a distance supervised relation extraction approach for long-tailed, imbalanced data which is prevalent in real-world settings. Here, the challenge is to learn accurate “few-shot” models for classes existing at the tail of the class distribution, for which little data is available. Inspired by the rich semantic correlations between classes at the long tail and those at the head, we take advantage of the knowledge from data-rich classes at the head of the distribution to boost the performance of the data-poor classes at the tail. First, we propose to leverage implicit relational knowledge among class labels from knowledge graph embeddings and learn explicit relational knowledge using graph convolution networks. Second, we integrate that relational knowledge into relation extraction model by coarse-to-fine knowledge-aware attention mechanism. We demonstrate our results for a large-scale benchmark dataset which show that our approach significantly outperforms other baselines, especially for long-tail relations.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhiyuan Liu
2. Maosong Sun
3. Philip S. Yu
4. Xu Han
5. Erik Cambria
6. Yankai Lin
7. Jie Zhou
8. Peng Li

Citations in the corpus

• A Two-phase Prototypical Network Model for Incremental Few-shot Relation Classification (2020, background): “Currently, conventional supervised (Zeng et al., 2014; Chen et al., 2020) or distantly supervised (Mintz et al., 2009; Zhang et al., 2019) RC models are widely used and achieve remarkable performance.”
• Imbalanced Continual Learning with Partitioning Reservoir Sampling (2020, background): “Other works such as [27] and [72] define the minority classes as less than 100 or 200 samples in the training set, respectively.”
• Knowledge Graphs: Opportunities and Challenges (2023, background): “One of the biggest problems in this space is fake news (Zhang et al. 2019a).”
• A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, background): “[199] CNN/PCNN (sentence) + GCN + Knowledge-aware attention external KG, position embeddings”
• More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020, methodology): “…DS data has also been explored, such as incorporating KGs as external information to guide instance selection (Ji et al., 2017; Han et al., 2018b; Zhang et al., 2019a; Qu et al., 2019) and adopting multi-lingual corpora for the information consistency and complementarity (Verga et al., 2016; Lin…”
• AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction (2021, background): “RE appeals to many researchers (Zhang et al., 2017, 2018a, 2019; Nan et al., 2020; Wu et al., 2021) due to the capability to extract textual information and benefit many NLP applications (e.g., information retrieval, dialog generation, and question answering).”
• A Survey on Knowledge Graphs: Representation, Acquisition, and Applications (2020, methodology): “Inspired by the diachronic word embedding, Goel et al. [182] CNN + max pooling position embedding Multi CNN [137] Multi-window convolution + max pooling position embedding PCNN [138] CNN + piecewise max pooling position embedding MIMLCNN [139] CNN + piecewise and cross-sentence max pooling position ”
• Graph convolutional networks: a comprehensive review (2019, unknown): “Graph convolutional networks have been designed to the relation extraction between words [100, 101] and event extraction [102, 103].”