GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction
By Tsu-Jui Fu, Peng-Hsuan Li, Wei-Yun Ma. Annual Meeting of the Association for Computational Linguistics, 2019
386 citations recorded by the source corpus.
In this paper, we present GraphRel, an end-to-end relation extraction model which uses graph convolutional networks (GCNs) to jointly learn named entities and relations. In contrast to previous baselines, we consider the interaction between named entities and relations via a 2nd-phase relation-weighted GCN to better extract relations. Linear and dependency structures are both used to extract both sequential and regional features of the text, and a complete word graph is further utilized to extract implicit features among all word pairs of the text. With the graph-based approach, the prediction for overlapping relations is substantially improved over previous sequential approaches. We evaluate GraphRel on two public datasets: NYT and WebNLG. Results show that GraphRel maintains high precision while increasing recall substantially. Also, GraphRel outperforms previous work by 3.2% and 5.8% (F1 score), achieving a new state-of-the-art for relation extraction.
View Paper: https://www.semanticscholar.org/paper/6acacb9c81e67b50b218d173cb4022a1a5859191
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
Citations in the corpus
- Refining Sample Embeddings with Relation Prototypes to Enhance Continual Relation Extraction (2021, background): “(3) Graph neural networks (GNNs) (Zhang et al., 2018b; Fu et al., 2019; Zhu et al., 2019) build word/entity graphs for cross-sentence reasoning.”
- A Novel Cascade Binary Tagging Framework for Relational Triple Extraction (2019, methodology): “This is in contrast to previous approaches like (Fu et al., 2019) where the training objective is defined separately for entities and relations without explicitly modeling their integration at the triple level.”
- A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, methodology): “Dynamic Graph-based Model GP-GNNs [233] Bi-LSTM GCNs MLP + softmax Inter-node graph with generated parameters EoG [232] BiLSTM GCNN Node-feature aggregation + softmax Sentence-mention-entity pair graph GraphRel [220] BiLSTM BiGCN Threshold-based Relation-weighted graph DyGIE [238] ELmo + BiLSTM GCN ”
- A Frustratingly Easy Approach for Entity and Relation Extraction (2021, methodology): “…in (Miwa and Sasaki, 2014); Katiyar and Cardie (2017) and Zheng et al. (2017) employ sequence tagging-based approaches; Sun et al. (2019) and Fu et al. (2019) propose graph-based approaches to jointly predict entity and relation types; and, Li et al. (2019) convert the task into a…”
- A Joint Neural Model for Information Extraction with Global Features (2020, methodology): “…develop joint neural models to perform extraction of two IE subtasks, such as entity and relation extraction (Zheng et al., 2017; Katiyar and Cardie, 2017; Bekoulis et al., 2018; Fu et al., 2019; Luan et al., 2019; Sun et al., 2019) and event and temporal relation extraction (Han et al., 2019).”
- BioGPT: Generative Pre-trained Transformer for Biomedical Text Generation and Mining (2022, methodology): “Table filling methods formulate the task as a table constituted by the Cartesian product of itself and predicts the relations between the token pairs [39, 40, 41].”
- Knowledge Graphs: Opportunities and Challenges (2023, methodology): “Three main methods of knowledge acquisition are relation extraction, entity extraction, and attribute extraction (Fu et al. 2019).”