Semi-supervised Convolutional Neural Networks for Text Categorization via Region Embedding

By Rie Johnson, Tong Zhang. 2015

354 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

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function (2019, methodology): “Previous work regarding the application of SSL to this task includes training Naive Bayes model on unlabeled data using expectation-maximization algorithm [22], incorporation of multi-view embeddings representation of input words along with its one-hot representation as model’s input [9], use of add”
Deep Pyramid Convolutional Neural Networks for Text Categorization (2017, methodology): “Note that ShallowCNN enhanced with unsupervised embeddings (row 2) was originally proposed in (Johnson and Zhang, 2015b) as a semi-supervised extension of (Johnson and Zhang, 2015a), and then it was tested on the large datasets in (Johnson and Zhang, 2016).”
Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning (2016, background): “We show through numerous experiments that this combination leads to a competitive semi-supervised learning method.”
A Sensitivity Analysis of (and Practitioners’ Guide to) Convolutional Neural Networks for Sentence Classification (2015, background): “Kim (2014) defined a one-layer CNN architecture that performed comparably.”
Recent Trends in Deep Learning Based Natural Language Processing (2017, methodology): “Such differences were seen in many works like (Johnson and Zhang, 2015), where performance on longer text worked well as opposed to shorter texts.”
Representation learning for very short texts using weighted word embedding aggregation (2016, methodology): “One possibility is to use an multilayer perceptron (MLP) with the whole sentence as an input, or a 1D convolutional neural network (Collobert et al. (2011); Hu et al. (2014); Xu et al. (2015); Johnson and Zhang (2015)).”
Well-Read Students Learn Better: The Impact of Student Initialization on Knowledge Distillation (2019, methodology): “While feature-based unsupervised representations have been successfully used in compact models (Johnson & Zhang, 2015; Gururangan et al., 2019), inter alia , the pretraining+ﬁne-tuning approach has not been studied in depth for such small models.”
Supervised and Semi-Supervised Text Categorization using LSTM for Region Embeddings (2016, background): “In particular, let us ﬁrst focus on one-hot CNN which we proposed in JZ15 (Johnson & Zhang, 2015a;b).”
Rationale-Augmented Convolutional Neural Networks for Text Classification (2016, background): “Here we consider an alternative scenario in which we assume that we are provided a set of rationales (Zaidan et al., 2007; Zaidan and Eisner, 2008; McDonnell et al., 2016) in addition to instance labels, i.e., sentences or snippets that support the corresponding document categorizations.”
Alibaba’s Neural Machine Translation Systems for WMT18 (2018, methodology): “Similar to Chen and Huang (2016), we also make full use of conText (Johnson and Zhang, 2015) as the CNN-based text classiﬁer, which features a stack of two independent CNNs.”
Adversarial Attacks on Deep Learning Models in Natural Language Processing: A Survey (2019, methodology): “[118] conducted evaluation on three tasks: sentiment analysis (IMDB movie review, Elec [56], Rotten Tomatoes [103]), text categorization (DBpedia Ontology dataset and RCV1 [73]) and grammatical error detection (FCE-public [150]).”
Interpretable Adversarial Perturbation in Input Embedding Space for Text (2018, methodology): “For SEC, we used the following well-studied benchmark datasets, IMDB [ Maas et al. , 2011 ] , Elec [ Johnson and Zhang, 2015 ] , and Rotten Tomatoes [ Pang and Lee, 2005 ] .”
A Survey on Deep Semi-Supervised Learning (2021, background): “Answers [106], IMDB [107], Yelp review [104], Snippets [108], Ohsumed [109], TagMyNews [110], MR [111], Elec [112], Rotten Tomatoes [111], RCV1 [113] [114], [115], [116], [117], [118], [119] Dialogue policy learning MultiWOZ [120] [121] Dialogue generation Cornell Movie Dialogs Corpus [122], Ubuntu ”
Convolutional Neural Networks for Text Categorization: Shallow Word-level vs. Deep Character-level (2016, methodology): “See also the supplementary material of [4] for the representation power analysis.”
Investigating the Working of Text Classifiers (2018, background): “They also learn multi-view region embeddings through semi-supervised learning and incorporate them as additional features to further improve the model’s performance (Johnson and Zhang, 2015b).”
Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification (2020, methodology): “Employing modern neural networks for aspectbased sequence-level sentiment classification task, such as CNNs (Kim, 2014; Johnson and Zhang, 2015), RNNs (Castellucci et al.”
Natural Language Processing Advancements By Deep Learning: A Survey (2020, methodology): “A variety of CNN architectures were used in various classification tasks such as Sentiment Analysis and Topic Categorization [22], [25]–[27].”
A Survey on Text Classification: From Traditional to Deep Learning (2020, background): “[183] propose a CNN model based on two-view semi-supervised learning for text classification, which first uses unlabeled data to train the embedding of text regions and then labeled data.”
Transformation Networks for Target-Oriented Sentiment Classification (2018, background): “By this token, Convolutional Neural Networks (CNNs)—whose capability for extracting the informative n-gram features (also called “active local features”) as sentence representations has been verified in (Kim, 2014; Johnson and Zhang, 2015)— should be a suitable model for this classification problem.”