Paper: Named Entity Recognition With Long Short-Term Memory

ACL ID W03-0426
Title Named Entity Recognition With Long Short-Term Memory
Venue International Conference on Computational Natural Language Learning
Session Main Conference
Year 2003
Authors

In this approach to named entity recognition, a recurrent neural network, known as Long Short-Term Memory, is applied. The network is trained to perform 2 passes on each sentence, outputting its decisions on the second pass. The first pass is used to acquire information for dis- ambiguation during the second pass. SARD- NET, a self-organising map for sequences is used to generate representations for the lexical items presented to the LSTM network, whilst orthogonal representations are used to repre- sent the part of speech and chunk tags.