A Neural Layered Model for Nested Named Entity Recognition

Entity mentions embedded in longer entity mentions are referred to as nested entities. Most named entity recognition (NER) systems deal only with the flat entities and ignore the inner nested ones, which fails to capture finer-grained semantic information in underlying texts... (read more)

PDF Abstract

Datasets


Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Nested Mention Recognition ACE 2005 Neural layered model F1 72.2 # 9
Named Entity Recognition ACE 2005 Neural layered model F1 72.2 # 11
Nested Named Entity Recognition ACE 2005 Neural layered model F1 72.2 # 11
Named Entity Recognition GENIA Neural layered model F1 74.7 # 8
Nested Named Entity Recognition GENIA Neural layered model F1 74.7 # 11

Methods used in the Paper


METHOD TYPE
Sigmoid Activation
Activation Functions
Tanh Activation
Activation Functions
CRF
Structured Prediction
LSTM
Recurrent Neural Networks