Multi-Task Transfer Learning for Fine-Grained Named Entity Recognition

Masato Hagiwara, Ryuji Tamaki, Ikuya Yamada
2019 Text Analysis Conference  
This paper describes Studio Ousia's participation to the EDL track of TAC KBP 2019-(ultra) fine-grained named entity recognition (NER). The proposed system first trains a YAGO-based ultra fine-grained NER model in a multi-label, multi-task fashion. The pretrained model is then fine-tuned to adopt it to the AIDA taxonomy by adding a lightweight conversion layer. The experiments have shown that this transfer learning approach outperforms a simpler direct method which directly trains the YAGO-based NER model.
dblp:conf/tac/HagiwaraTY19 fatcat:27mwd5amunaqrcvfhn3mmxenrm