TDGI: Translation-Guided Double-Graph Inference for Document-Level Relation Extraction
Zhang, Lingling Zhong, Yujie Zheng, Qinghua Liu, Jun Wang, Qianying Wang, Jiaxin Chang, Xiaojun
Zhang, Lingling
Zhong, Yujie
Zheng, Qinghua
Liu, Jun
Wang, Qianying
Wang, Jiaxin
Chang, Xiaojun
Supervisor
Department
Computer Vision
Embargo End Date
Type
Journal article
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Document-level relation extraction (DocRE) aims at predicting relations of all entity pairs in one document, which plays an important role in information extraction. DocRE is more challenging than previous sentence-level relation extraction, as it often requires coreference and logical reasoning across multiple sentences. Graph-based methods are the mainstream solution to this complex reasoning in DocRE. They generally construct the heterogeneous graphs with entities, mentions, and sentences as nodes, co-occurrence and co-reference relations as edges. Their performance is difficult to further break through because the semantics and direction of the relation are not jointly considered in graph inference process. To this end, we propose a novel translation-guided double-graph inference network named TDGI for DocRE. On one hand, TDGI includes two relation semantics-aware and direction-aware reasoning graphs, i.e., mention graph and entity graph, to mine relations among long-distance entities more explicitly. Each graph consists of three elements: vectorized nodes, edges, and direction weights. On the other hand, we devise an interesting translation-based graph updating strategy that guides the embeddings of mention/entity nodes, relation edges, and direction weights following the specific translation algebraic structure, thereby to enhance the reasoning skills of TDGI. In the training procedure of TDGI, we minimize the relation multi-classification loss and triple contrastive loss together to guarantee the model’s stability and robustness. Comprehensive experiments on three widely-used datasets show that TDGI achieves outstanding performance comparing with state-of-the-art baselines
Citation
L. Zhang et al., "TDGI: Translation-Guided Double-Graph Inference for Document-Level Relation Extraction," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 4, pp. 2647-2659, April 2025, doi: 10.1109/TPAMI.2025.3528246
Source
IEEE Transactions on Pattern Analysis and Machine Intelligence
Conference
Keywords
Cognition, Translation, Semantics, Transformers, Data mining, Electronic mail, Context modeling, Vectors, Training, Robustness
Subjects
Source
Publisher
IEEE