Table 1: 
Specifications of variants of ELMo models compared in Sections 4 and 5. Cont means the model has continuous outputs. LN means layer normalization.
ModelInputSequence EncoderOutput
ELMo CNN LSTM Sampled Softmax 
ELMo-C (ours) FastTextcc LSTM w/ LN Cont w/ FastTextcc 
ELMo-A FastTextcc LSTM w/ LN Adaptive Softmax 
ELMo-Sub Subword LSTM w/ LN Softmax 
 
ELMo-COneB FastTextOneB LSTM w/ LN Cont w/ FastTextOneB 
ELMo-CRnd FastTextcc LSTM w/ LN Cont w/ Random Embedding 
ELMo-CCNN Trained CNN LSTM w/ LN Cont w/ Trained CNN 
ELMo-CCNN-CC Trained CNN LSTM w/ LN Cont w/ FastTextcc 
ELMo-CCC-CNN FastTextcc LSTM w/ LN Cont w/ Trained CNN 
ModelInputSequence EncoderOutput
ELMo CNN LSTM Sampled Softmax 
ELMo-C (ours) FastTextcc LSTM w/ LN Cont w/ FastTextcc 
ELMo-A FastTextcc LSTM w/ LN Adaptive Softmax 
ELMo-Sub Subword LSTM w/ LN Softmax 
 
ELMo-COneB FastTextOneB LSTM w/ LN Cont w/ FastTextOneB 
ELMo-CRnd FastTextcc LSTM w/ LN Cont w/ Random Embedding 
ELMo-CCNN Trained CNN LSTM w/ LN Cont w/ Trained CNN 
ELMo-CCNN-CC Trained CNN LSTM w/ LN Cont w/ FastTextcc 
ELMo-CCC-CNN FastTextcc LSTM w/ LN Cont w/ Trained CNN 
View Large
Close Modal
This Feature Is Available To Subscribers Only

or Create an Account

Close Modal
Close Modal
This site uses cookies. By continuing to use our website, you are agreeing to our privacy policy. No content on this site may be used to train artificial intelligence systems without permission in writing from the MIT Press.
Accept