search

jpWang / LiLT

Official PyTorch implementation of LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding (ACL 2022)
MIT License
335 stars 40 forks source link

"linking" in Dataset and IOB Tagging #8

Closed vibeeshan025 closed 2 years ago

vibeeshan025 commented 2 years ago

The en.train.json contains a linking filed array. Is it required for SER ( Semantic Entity Recognition instead of RE) tasks?

Have you ever tried IOB tagging for multiple word outputs?

jpWang commented 2 years ago
  1. No.
  2. This repo follows LayoutLM family's style. You can feel free to use IOB tagging + CRF. Generally, it can further improve performance.