Semi-supervised condensed nearest neighbor for part-of-speech tagging

By Anders Søgaard. 2011

66 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.

Citations in the corpus

End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF (2016, methodology): “Comparing with traditional statistical models, our system achieves state-of-the-art accuracy, obtaining 0.05% improvement over the previously best reported results by Søgaard (2011).”
Bidirectional LSTM-CRF Models for Sequence Tagging (2015, background): “In this paper, we systematically compared the performance of LSTM networks based models for se-Table (Gimenez and Marquez, 2004) 97.16 No Bidirectional perceptron learning (Shen et al., 2007) 97.33 No Semi-supervised condensed nearest neighbor 97.50 Yes (Soegaard, 2011) CRFs with structure regulariz”
Empower Sequence Labeling with Task-Aware Neural Language Model (2017, background): “ a single-layer LSTM with 2048 hidden units and a 512-dimension projection unit. Ind & Model Accuracy Type Value (std) 0) Collobert et al. 2011y reported 97.29 16) Manning 2011 reported 97.28 17) Søgaard 2011 reported 97.50 18) Sun 2014 reported 97.36 13) Lample et al. 2016y meanstd 97.350.09 ma”
Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation (2015, unknown): “44 SCCN (Søgaard, 2011) yes yes 97.”
Learning Character-level Representations for Part-of-Speech Tagging (2014, methodology): “In order to fairly compare our results with previous work, we adopt the same partitions used by other researchers (Manning, 2011; Søgaard, 2011; Collobert et al., 2011).”
Ask Me Anything: Dynamic Memory Networks for Natural Language Processing (2015, methodology): “The previous best model for part-of-speech tagging on the Wall Street Journal section of the Penn Tree Bank (Marcus et al., 1993) was So-gaard (Søgaard, 2011) who used a semisupervised nearest neighbor approach.”
Multi-Task Cross-Lingual Sequence Tagging from Scratch (2016, background): “Currently, however, the best results on speciﬁc sequence-tagging tasks are usually achieved by approaches that target only one speciﬁc task, either POS tagging (Søgaard, 2011; Toutanova et al., 2003), chunking (Shen and Sarkar, 2005), or NER (Luo et al., 2015; Pas-sos et al., 2014).”