The AutoKnow system performs data imputation by extracting attribute-value pairs from product data using a taxonomy-aware tagging approach that leverages Conditional Random Fields (CRF) combined with multi-task learning and a shared BiLSTM to train sequence tagging and product type categorization.

Authors

• Person: Not available Organization: arXiv
  Construction of Knowledge Graphs: State and Challenges - arXiv

Sources

• Construction of Knowledge Graphs: State and Challenges - arXiv arxiv.org arXiv via serper

Referenced by nodes (2)

• multi-task learning concept
• AutoKnow entity