Named entity recognition can deeply explore semantic features and enhance the ability of vector representation text data. This paper proposes a named method based on multi-head attention to aim at problem fuzzy lexical boundary in Chinese recognition. Firstly, Word2vec is used extract word vectors, HMM ALBERT character Feedforward-attention mechanism fuse three then fused vectors remove by BiLS...

Abstract We study learning named entity recognizers in the presence of missing annotations. approach this setting as tagging with latent variables and propose a novel loss, Expected Entity Ratio, to learn models systematically tags. show that our is both theoretically sound empirically useful. Experimentally, we find it meets or exceeds performance strong state-of-the-art baselines across varie...

Current work in named entity recognition (NER) uses either cross entropy (CE) or conditional random fields (CRF) as the objective/loss functions to optimize underlying NER model. Both of these traditional objective for problem generally produce adequate performance when data distribution is balanced and there are sufficient annotated training examples. But since inherently an imbalanced tagging...