Global Entity Disambiguation with Pretrained Contextualized Embeddings of Words and Entities

We propose a new global entity disambiguation (ED) model based on contextualized embeddings of words and entities. Our model is based on a bidirectional transformer encoder (i.e., BERT) and produces contextualized embeddings for words and entities in the input text... (read more)

PDF Abstract
No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Entity Disambiguation ACE2004 MEP + pseudo entities Micro-F1 91.5 # 2
Entity Disambiguation ACE2004 confidence-order Micro-F1 91.9 # 1
Entity Disambiguation AIDA-CoNLL MEP In-KB Accuracy 94.3 # 5
Entity Disambiguation AIDA-CoNLL confidence-order In-KB Accuracy 95.0 # 1
Entity Disambiguation AQUAINT confidence-order Micro-F1 93.5 # 2
Entity Disambiguation AQUAINT MEP + pseudo entities Micro-F1 93.7 # 1
Entity Disambiguation MSNBC confidence-order Micro-F1 96.3 # 1
Entity Disambiguation MSNBC MEP Micro-F1 94.1 # 3
Entity Disambiguation WNED-CWEB MEP Micro-F1 76.2 # 4
Entity Disambiguation WNED-CWEB confidence-order Micro-F1 78.9 # 1
Entity Disambiguation WNED-WIKI confidence-order Micro-F1 89.1 # 1
Entity Disambiguation WNED-WIKI MEP Micro-F1 86.2 # 3

Methods used in the Paper


METHOD TYPE
Residual Connection
Skip Connections
BPE
Subword Segmentation
Dense Connections
Feedforward Networks
Label Smoothing
Regularization
ReLU
Activation Functions
Adam
Stochastic Optimization
Softmax
Output Functions
Dropout
Regularization
Multi-Head Attention
Attention Modules
Layer Normalization
Normalization
Scaled Dot-Product Attention
Attention Mechanisms
Transformer
Transformers