发布

  • v0.1 dc600281c6

    add NER state-of-the-art result (#296)

    frostbyte_neo 发布于 2020-01-18 09:20:08 +00:00 | 188 次提交 在此版本后已推送到 master

    Add NER state-of-the-art result with EMNLP 2018 paper (Learning Better Internal Structure of Words for Sequence Labeling), this paper proposed IntNet, which mainly focus on learning better character-to-word representations, IntNet significantly outperformed other character embedding models, and also combined with BiLSTM-CRF achieved state-of-the-art NER result without using any lexical features, transfer learning, language modeling or pre-training.

    下载附件