TCN: Table Convolutional Network for Web Table Interpretation

@article{Wang2021TCNTC,
  title={TCN: Table Convolutional Network for Web Table Interpretation},
  author={Daheng Wang and Prashant Shiralkar and Colin Lockard and Binxuan Huang and X. Dong and Meng Jiang},
  journal={Proceedings of the Web Conference 2021},
  year={2021}
}
Information extraction from semi-structured webpages provides valuable long-tailed facts for augmenting knowledge graph. Relational Web tables are a critical component containing additional entities and attributes of rich and diverse knowledge. However, extracting knowledge from relational tables is challenging because of sparse contextual information. Existing work linearize table cells and heavily rely on modifying deep language models such as BERT which only captures related cells… Expand

Figures and Tables from this paper

References

SHOWING 1-8 OF 8 REFERENCES
Learning Semantic Annotations for Tabular Data
TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
Table2Vec: Neural Word and Entity Embeddings for Table Population and Retrieval
Effective and efficient Semantic Table Interpretation using TableMiner+
  • Z. Zhang
  • Computer Science
  • Semantic Web
  • 2017
A Comprehensive Survey on Graph Neural Networks
Attention is All you Need
How Powerful are Graph Neural Networks?
TURL: Table Understanding through Representation Learning