Bag of Tricks for Efficient Text Classification

@inproceedings{Joulin2017BagOT,
  title={Bag of Tricks for Efficient Text Classification},
  author={Armand Joulin and Edouard Grave and Piotr Bojanowski and Tomas Mikolov},
  booktitle={EACL},
  year={2017}
}
This paper explores a simple and efficient baseline for text classification. Our experiments show that our fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation. We can train fastText on more than one billion words in less than ten minutes using a standard multicore CPU, and classify half a million sentences among 312K classes in less than a minute. 
Exploring Labels Discriminating Power of Words in Label Embeddings for Text Classification
Recent studies have shown that simple models are efficient and interpretable in text classification tasks , and have the potential to outperform sophisticated deep neural models. Existing approachesExpand
An Efficient Text Classification Using fastText for Bahasa Indonesia Documents Classification
TLDR
This paper aims to compare text classification using the TFIDF model as one of the BOW models with a fastText model for 500 news articles in Bahasa Indonesia and concludes that the fast text model is efficient text classification. Expand
An Analysis of Hierarchical Text Classification Using Word Embeddings
TLDR
An analysis indicates that using word embeddings and its flavors is a very promising approach for HTC. Expand
Low-Dimensional Classification of Text Documents
TLDR
The fastText algorithm is studied in terms of its ability to find and extract well distinguishable characteristics for a text corpora to overcome a common belief that accurate subject classification of text documents must involve high dimensional feature vectors. Expand
Do Convolutional Networks need to be Deep for Text Classification ?
TLDR
This work shows on 5 standard text classification and sentiment analysis tasks that deep models indeed give better performances than shallow networks when the text input is represented as a sequence of characters, but a simple shallow-and-wide network outperforms deep models such as DenseNet with word inputs. Expand
Intent Detection System Based on Word Embeddings
TLDR
The results show that the intent detection system based on FastText word embeddings and neural network classifier provides state-of-the-art results on three English datasets outperforming many popular services. Expand
Fast and Efficient Text Classification with Class-based Embeddings
TLDR
A novel neural network architecture for ultra-fast, memory-efficient text classification based on word embeddings trained directly over the class space, which allows for fast, efficient, and effective text classification. Expand
Deep Learning- and Word Embedding-Based Heterogeneous Classifier Ensembles for Text Classification
TLDR
Experimental results demonstrate that the usage of heterogeneous ensembles together with deep learning methods and word embeddings enhances the classification performance of texts. Expand
A Hierarchical Neural Attention-based Text Classifier
TLDR
This work uses external knowledge in the form of topic category taxonomies to aide the classification by introducing a deep hierarchical neural attention-based classifier that performs better than or comparable to state-of-the-art hierarchical models at significantly lower computational cost while maintaining high interpretability. Expand
2 Related work : popular models for text classification
Deep neural networks are in vogue for text classification. The lack of interpretability and computational cost associated with deep architectures has led to renewed interest in effective baselineExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
Character-level Convolutional Networks for Text Classification
TLDR
This article constructed several large-scale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results in text classification. Expand
Text Categorization with Support Vector Machines: Learning with Many Relevant Features
This paper explores the use of Support Vector Machines (SVMs) for learning text classifiers from examples. It analyzes the particular properties of learning with text data and identifies why SVMs areExpand
Convolutional Neural Networks for Sentence Classification
TLDR
The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors. Expand
Efficient Character-level Document Classification by Combining Convolution and Recurrent Layers
TLDR
A neural network architecture that utilizes both convolution and recurrent layers to efficiently encode character inputs is proposed and validated on eight large scale document classification tasks and compared with character-level convolution-only models. Expand
Efficient Estimation of Word Representations in Vector Space
TLDR
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities. Expand
Distributed Representations of Sentences and Documents
TLDR
Paragraph Vector is an unsupervised algorithm that learns fixed-length feature representations from variable-length pieces of texts, such as sentences, paragraphs, and documents, and its construction gives the algorithm the potential to overcome the weaknesses of bag-of-words models. Expand
Baselines and Bigrams: Simple, Good Sentiment and Topic Classification
TLDR
It is shown that the inclusion of word bigram features gives consistent gains on sentiment analysis tasks, and a simple but novel SVM variant using NB log-count ratios as feature values consistently performs well across tasks and datasets. Expand
Text Understanding from Scratch
TLDR
It is shown that temporal ConvNets can achieve astonishing performance without the knowledge of words, phrases, sentences and any other syntactic or semantic structures with regards to a human language. Expand
A comparison of event models for naive bayes text classification
TLDR
It is found that the multi-variate Bernoulli performs well with small vocabulary sizes, but that the multinomial performs usually performs even better at larger vocabulary sizes--providing on average a 27% reduction in error over the multi -variateBernoulli model at any vocabulary size. Expand
Very Deep Convolutional Networks for Text Classification
TLDR
This work presents a new architecture (VDCNN) for text processing which operates directly at the character level and uses only small convolutions and pooling operations, and is able to show that the performance of this model increases with the depth. Expand
...
1
2
3
4
...