Baselines and Bigrams: Simple, Good Sentiment and Topic Classification

By Sida I. Wang, Christopher D. Manning. 2012

1,360 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

Semi-supervised Sequence Learning (2015, neutral): “77% NBSVM-bi (Naı̈ve Bayes SVM with bigrams) [35] 8.”
Skip-Thought Vectors (2015, background): “In particular, the NB-SVM of [37] is a fast and robust performer on these tasks.”
Distributed Representations of Sentences and Documents (2014, methodology): “…(Maas et al., 2011) 11.11% WRRBM (Dahl et al., 2012) 12.58% WRRBM + BoW (bnc) (Dahl et al., 2012) 10.77% MNB-uni (Wang & Manning, 2012) 16.45% MNB-bi (Wang & Manning, 2012) 13.41% SVM-uni (Wang & Manning, 2012) 13.05% SVM-bi (Wang & Manning, 2012) 10.84% NBSVM-uni (Wang & Manning, 2012) 11.71%…”
Representation Learning with Contrastive Predictive Coding (2018, background): “We found that more advanced sentence encoders did not signiﬁcantly improve the results, which may be due to the simplicity of the transfer tasks (e.g., in MPQA most datapoints consists of one or a few words), and the fact that bag-of-words models usually perform well on many NLP tasks [48].”
Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, methodology): “• Bigram: LR model also incorporating bigram features, known to be competitive on several text classification tasks (Wang and Manning, 2012).”
FastText.zip: Compressing text classification models (2016, methodology): “However, in other cases including several text classiﬁcation problems, it has been shown that deep networks do not convincingly beat the prior state of the art techniques (Wang & Manning, 2012; Joulin et al., 2016).”
Convolutional Neural Networks for Sentence Classification (2014, methodology): “3 MNB (Wang and Manning, 2012) 79.”
Bag of Tricks for Efficient Text Classification (2016, background): “Despite their simplicity, they often obtain state-of-the-art performances if the right features are used (Wang and Manning, 2012).”
Hierarchical Attention Networks for Document Classification (2016, methodology): “Traditional approaches of text classiﬁcation represent documents with sparse lexical features, such as n -grams, and then use a linear model or kernel methods on this representation (Wang and Manning, 2012; Joachims, 1998).”
Self-Adaptive Hierarchical Sentence Model (2015, methodology): “NB-SVM and MNB. Naive Bayes SVM and Multinomial Naive Bayes with uni and bigram features [Wang and Manning, 2012].”
Performance Impact Caused by Hidden Bias of Training Data for Recognizing Textual Entailment (2018, methodology): “This paper employs a multinomial NB model (Wang and Manning, 2012) as the TE label prediction model, which is defined by the following equation:”
Graph Convolutional Networks for Text Classification (2018, background): “In addition, some more complex features have been designed, such as n-grams (Wang and Manning 2012) and entities in ontologies (Chenthamarakshan et al. 2011).”
Dropout Training as Adaptive Regularization (2013, methodology): “christian classification task described in [15].”