Named Entity Recognition with Long Short-Term Memory
暂无分享,去创建一个
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 disambiguation during the second pass. SARDNET, 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 represent the part of speech and chunk tags.
[1] James Hammerton. Clause identification with long short-term memory , 2001, CoNLL.
[2] Juergen Schmidhuber,et al. Long Short-Term Memory Learns Context Free and Context Sensitive Languages , 2000 .
[3] Risto Miikkulainen,et al. SARDNET: A Self-Organizing Feature Map for Sequences , 1994, NIPS.
[4] Jürgen Schmidhuber,et al. Long Short-Term Memory , 1997, Neural Computation.
[5] Jakub Zavrel,et al. The Language Environment and Syntactic Word-Class Acquisition. , 1996 .