Attention Guided Graph Convolutional Networks for Relation Extraction

By Zhijiang Guo, Yan Zhang, Wei Dang Lu. Annual Meeting of the Association for Computational Linguistics, 2019

461 citations recorded by the source corpus.

Dependency trees convey rich structural information that is proven useful for extracting relations among entities in text. However, how to effectively make use of relevant information while ignoring irrelevant information from the dependency trees remains a challenging research question. Existing approaches employing rule based hard-pruning strategies for selecting relevant partial dependency structures may not always yield optimal results. In this work, we propose Attention Guided Graph Convolutional Networks (AGGCNs), a novel model which directly takes full dependency trees as inputs. Our model can be understood as a soft-pruning approach that automatically learns how to selectively attend to the relevant sub-structures useful for the relation extraction task. Extensive results on various tasks including cross-sentence n-ary relation extraction and large-scale sentence-level relation extraction show that our model is able to better leverage the structural information of the full dependency trees, giving significantly better results than previous approaches.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/e4363d077a890c8d5c5e66b82fe69a1bbbdd5c80

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

Citations in the corpus

Aligning Cross-Lingual Entities with Multi-Aspect Information (2019, background): “…(GCNs) (Kipf and Welling, 2017) are variants of convolutional networks that have proven effective in capturing information from graph structures, such as dependency graphs (Guo et al., 2019b), abstract meaning representation graphs (Guo et al., 2019a), and knowledge graphs (Wang et al., 2018).”
Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling (2020, methodology): “, 2020), and then perform inference with graph neural models (Liang et al., 2016; Guo et al., 2019).”
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking (2020, background): “…database schemas) and shown effective on a range of tasks, including relation extraction (Zhang et al., 2018; Zhu et al., 2019; Sun et al., 2019a; Guo et al., 2019), question answering (Sorokin & Gurevych, 2018; Sun et al., 2018; De Cao et al., 2019), syntactic and semantic parsing tasks…”
NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction (2020, background): “, attention CNN [32], attention RNN [38, 39], and GCN [7, 37]).”
KnowPrompt: Knowledge-aware Prompt-tuning with Synergistic Optimization for Relation Extraction (2021, methodology): “Early approaches involve pattern-based methods [8, 29], CNN/RNN-based [56, 62, 65] and graph-based methods [19, 20, 61].”
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 ”
A Comprehensive Survey on Automatic Knowledge Graph Construction (2023, methodology): “For instance, for n-ary relation extraction, AGGCN [171] links the roots of dependency trees of adjacent sentences via attention-guided GCN layers, which also overcomes the reliance on semantic role labeling.”
AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction (2021, methodology): “, 2017) and graph-based (Zhang et al., 2018b; Guo et al., 2019) models, etc.”
HELoC: Hierarchical Contrastive Learning of Source Code Representation (2022, background): “Previous source code representations [31, 32] have demonstrated that GNNs can better encode the local structure of ASTs [33].”