Learning Character-level Representations for Part-of-Speech Tagging

By C. D. Santos, Bianca Zadrozny. 2014

606 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Character-level Convolutional Networks for Text Classification (2015, methodology): “In particular, these ConvNet approaches use words as a basis, in which character-level features extracted at word [28] or word n-gram [29] level form a distributed representation.”
Character-Aware Neural Language Models (2015, background): “This was surprising, as improvements have been reported on part-of-speech tagging (dos Santos and Zadrozny 2014) and named entity recognition (dos Santos and Guimaraes 2015) by concatenating word embeddings with the output from a character-level CNN.”
Training Neural Networks Using Features Replay (2018, background): “In recent years, the deep convolutional neural networks have made great breakthroughs in computer vision [8, 10, 19, 20, 32, 33], natural language processing [15, 16, 31, 36], and reinforcement learning [21, 23, 24, 25].”
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling (2018, methodology): “ConvNets were subsequently applied to NLP tasks such as part-of-speech tagging and semantic role labelling (Collobert & Weston, 2008; Col-lobert et al., 2011; dos Santos & Zadrozny, 2014).”
Recent Trends in Deep Learning Based Natural Language Processing (2017, background): “In (Santos and Zadrozny, 2014), the authors did not consider CRF, but since word-level decision was made on a context window, it can be seen that dependencies were modeled implicitly.”
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF (2016, methodology): “This is consistent with , 2014; Chiu and Nichols, 2015).”
Character-based Neural Machine Translation (2016, background): “for POS tagging (Santos and Zadrozny, 2014), name entity recognition (Santos and aes, 2015), parsing (Ballesteros et al.”
A Primer on Neural Network Models for Natural Language Processing (2015, background): “…(Dong, Wei, Zhou, & Xu, 2015), predicting box-office revenues of movies based on critic reviews (Bitvai & Cohn, 2015) modeling text interestingness (Gao, Pantel, Gamon, He, & Deng, 2014), and modeling the relation between character-sequences and part-of-speech tags (Santos & Zadrozny, 2014).”
Attentive Pooling Networks (2016, methodology): “Following dos Santos & Zadrozny (2014), we http://cs.jhu.edu/ ˜xuchen/packages/jacana-qa-naacl2013-data-results.tar.bz2 4 The data is obtained from (Yang et al., 2015) 5 https://code.google.com/p/word2vec/ set the learning rate for epoch t , λ t , using the equation: In our experiments, the four NN…”
Word Representation Models for Morphologically Rich Languages in Neural Machine Translation (2016, background): “Several authors have proposed convolutional neural networks over character sequences, as part of models of part of speech tagging (Santos and Zadrozny, 2014), language models (Kim et al., 2015) and machine translation (Costa-jussà and Fonollosa, 2016).”
Explaining Character-Aware Neural Networks for Word-Level Prediction: Do They Discover Linguistic Rules? (2018, positive): “Generally, two neural network architectures are con-2 sidered for aggregating the individual characters: a BiLSTM (Ling et al., 2015; Plank et al., 2016) or a CNN (dos Santos and Zadrozny, 2014; Bjerva et al., 2016; Heigold et al., 2017).”