concept recurrent neural network in category nlp
appears as: recurrent neural networks, A recurrent neural network

This is an excerpt from Manning's book Real-World Natural Language Processing.
These tags come from the Penn Treebank POS tagset, which is the most popular, standard corpus for training and evaluating various NLP tasks such as POS tagging and parsing. Traditionally, POS tagging was solved by sequential labeling algorithms such as hidden markov models (HMMs) and conditional random fields (CRFs). Recently, recurrent neural networks (RNNs) are a popular and practical choice for training a POS tagger with high accuracy. The results of POS tagging are often used as the input to other upstream NLP tasks, such as machine translation and parsing. I’ll cover part-of-speech tagging with more details in Chapter 5.
A recurrent neural network (RNN) is a neural network with a loop. It can transform a variable-length input to a fixed-length vector