Upgrade to PRO for Only $50/Year—Limited-Time Offer! 🔥

Fine grained Entity Typing using Graph Convolut...

Fine grained Entity Typing using Graph Convolutional Networks

In this presentation, only GCN basics are explained and mention encoder is not.

izuna385

May 23, 2019
Tweet

More Decks by izuna385

Other Decks in Technology

Transcript

  1. 2/13 Paper(Baseline) 2 Imposing Label-Relational Inductive Bias for Extremely Fine-Grained

    Entity Typing (Xiong et al, NAACL ’19) Task : Entity typing(multi-label prediction) RQ : Does Typing-Correlation encoding via GCN contributes Typing prediction? Approach : Add graph propagation layer to prediction module.
  2. 3/13 Task and Dataset (Choi et al, ACL ’18) 3

    • train/dev/test = 2000 * 3 •
  3. 4/13 Motivation for using GCN • Recent model for Entity

    typing incorporates pre-defined typing structure. • But there are lots of typing which are unseen in KB. • Without pre-defined structure, still label-correlation should be considered. (Shikhar et al, 2018) inconsistent
  4. 8/13 Incorporate structure-bias into prediction layer Linear transformation layer :encoded

    mention mention encoding (In this slide, this module isn’t explained.)
  5. 10/13 Incorporate structure-bias into prediction layer Linear transformation layer(learned) :encoded

    mention • Linear-transformation layer(prediction layer) can be seen as typing embedding matrix. • But, how to incorporate label-correlation?
  6. 11/13 Incorporate structure-bias into prediction layer Linear transformation layer :encoded

    mention Typing co- occurrence information (fixed) Typing matrix Propagation rule :learned :type-type correlation incorporated type-emb matrix
  7. 12/13 Evaluation and re-implementation result model P(test) R(test) F(test) Choi

    et al.(2018) 47.1 24.2 32.0 LabelGCN(paper) 50.3 29.2 36.9 LabelGCN(re-imp) 49.2 28.4 36.0 Hyperparameters are the same as original ones. Epochs are not written, so I stopped at 100 iter. No P-R curve (prob-threshold) tuning.(Threshold=0.5, same as Choi et al.)
  8. 13/13 Future work • Ablation study • Apply this model

    to another dataset/domain (OntoNotes, etc)