ACL Findings2021
HySPA: Hybrid Span Generation for Scalable Text-to-Graph Extraction
Liliang Ren, Chenkai Sun, Heng Ji, Julia Hockenmaier
Abstract
Text-to-Graph extraction aims to automatically extract information graphs consisting of mentions and types from natural language texts. Existing approaches, such as table filling and pairwise scoring, have shown impressive performance on various information extraction tasks, but they are difficult to scale to datasets with longer input texts because of their secondorder space/time complexities with respect to the input length. In this work, we propose a Hybrid SPan GenerAtor (HySPA) that invertibly maps the information graph to an alternating sequence of nodes and edge types, and directly generates such sequences via a hybrid span decoder which can decode both the spans and the types recurrently in linear time and space complexities. Extensive experiments on the ACE05 dataset show that our approach also significantly outperforms state-ofthe-art on the joint entity and relation extraction task. 1
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
5 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders cites ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
- Unified Structure Generation for Universal Information Extraction cites Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders
- Unified Structure Generation for Universal Information Extraction cites A Joint Neural Model for Information Extraction with Global Features
- Generative Knowledge Graph Construction: A Review cites A Novel Cascade Binary Tagging Framework for Relational Triple Extraction
- Generative Knowledge Graph Construction: A Review cites Unified Structure Generation for Universal Information Extraction
- Generative Knowledge Graph Construction: A Review cites CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning
- Generative Knowledge Graph Construction: A Review cites A Joint Neural Model for Information Extraction with Global Features
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction cites Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction cites Unified Structure Generation for Universal Information Extraction
Cited by top-tier papers5
- Generative Knowledge Graph Construction: A ReviewHongbin Ye, Ningyu Zhang, Hui Chen, Huajun ChenEMNLP 2022 · 51 citations
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation ExtractionUrchade Zaratiana, Nadi Tomeh, Pierre Holat, Thierry CharnoisAAAI 2024 · 39 citations
- A Generative Model for End-to-End Argument Mining with Reconstructed Positional Encoding and Constrained Pointer MechanismJianzhu Bao, Yuhang He, Yang Sun, Bin Liang et al.EMNLP 2022 · 15 citations
- Unified Structure Generation for Universal Information ExtractionYaojie Lu, Qing Liu, Dai Dai, Xinyan Xiao et al.ACL 2022
- Latent Constraints on Unsupervised Text-Graph Alignment with Information AsymmetryJidong Tian, Wenqing Chen, Yitian Li, Caoyun Fan et al.AAAI 2023
Builds on7
- ALBERT: A Lite BERT for Self-supervised Learning of Language RepresentationsZhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel et al.ICLR 2020 · 7,418 citations
- A Novel Cascade Binary Tagging Framework for Relational Triple ExtractionZhepei Wei, Jianlin Su, Yue Wang, Yuan Tian et al.ACL 2020 · 610 citations
- A Joint Neural Model for Information Extraction with Global FeaturesYing Lin, Heng Ji, Fei Huang, Lingfei WuACL 2020 · 376 citations
- Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence EncodersJue Wang, Wei LuEMNLP 2020 · 209 citations
- CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task LearningDaojian Zeng, Haoran Zhang, Qianying LiuAAAI 2020 · 205 citations
Related papers
- Text-to-Table: A New Way of Information ExtractionXueqing Wu, Jiacheng Zhang, Hang LiACL 2022
- Learning Reasoning Patterns for Relational Triple Extraction with Mutual Generation of Text and GraphYubo Chen, Yunqi Zhang, Yongfeng HuangACL Findings 2022 · 7 citations
- Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph ConstructionHaoran Luo, Haihong E, Yuhao Yang, Tianyu Yao et al.NeurIPS 2024 · 19 citations
- GDPNet: Refining Latent Multi-View Graph for Relation ExtractionFuzhao Xue, Aixin Sun, Hao Zhang, Eng Siong ChngAAAI 2021 · 90 citations
- Line Graph Enhanced AMR-to-Text Generation with Mix-Order Graph Attention NetworksYanbin Zhao, Lu Chen, Zhi Chen, Ruisheng Cao et al.ACL 2020 · 33 citations
