Investigating Lstm with k-Max Pooling for Text Classification

Shu, Bo; Ren, Fuji; Bao, Yanwei

doi:10.1109/icicta.2018.00015

Cited by 8 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, several studies have confirmed that the use of some modules in the feature aggregation stage can enhance the performance of the network and improve the classification accuracy. Shu et al 18 mined the LSTM network with K-MaxPooling and used K-MaxPooling for feature aggregation to achieve accurate text classification. You et al 19 developed an extreme multi-label text classification model based on Bi-LSTM and multi-label attention mechanisms.…”

Section: Related Workmentioning

confidence: 99%

Feature-enhanced text-inception model for Chinese long text classification

Guo

Jiayu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

To solve the problem regarding unbalanced distribution of multi-category Chinese long texts and improve the classification accuracy thereof, a data enhancement method was proposed. Combined with this method, a feature-enhanced text-inception model for Chinese long text classification was proposed. First, the model used a novel text-inception module to extract important shallow features of the text. Meanwhile, the bidirectional gated recurrent unit (Bi-GRU) and the capsule neural network were employed to form a deep feature extraction module to understand the semantic information in the text; K-MaxPooling was then used to reduce the dimension of its shallow and deep features and enhance the overall features. Finally, the Softmax function was used for classification. By comparing the classification effects with a variety of models, the results show that the model can significantly improve the accuracy of long Chinese text classification and has a strong ability to recognize long Chinese text features. The accuracy of the model is 93.97% when applied to an experimental dataset.

show abstract

Section: Related Workmentioning

confidence: 99%

Feature-enhanced text-inception model for Chinese long text classification

Guo

Jiayu

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This paper [34] proposes a method which uses Spatial-Dropout1D, LSTM and k-Max Pooling. The study states that word-level inputs are better than character-level inputs.…”

Section: Investigating Lstm With K-max Pooling For Text Classificationmentioning

confidence: 99%

<strong>Cooking is All About People: Comment Classification on Cookery Channels Using Bert and Classification Models (Malayalam-English Mix-Code)</strong>

Kazhuparambil

Kaushik

2020

Preprint

View full text Add to dashboard Cite

The scope of a lucrative career promoted by Google through its video distribution platform YouTube 1 has attracted a large number of users to become content creators. An important aspect of this line of work is the feedback received in the form of comments which show how well the content is being received by the audience. However, volume of comments coupled with spam and limited tools for comment classification makes it virtually impossible for a creator to go through each and every comment and gather constructive feedback. Automatic classification of comments is a challenge even for established classification models, since comments are often of variable lengths riddled with slang, symbols and abbreviations. This is a greater challenge where comments are multilingual as the messages are often rife with the respective vernacular. In this work, we have evaluated top-performing classification models and four different vectorizers, for classifying comments which are a mix of different combinations of English and Malayalam (only English, only Malayalam and Mix of English and Malayalam). The statistical analysis of results indicates that Multinomial Naïve Bayes, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest and Decision Trees offer similar level of accuracy in comment classification. Further, we have also evaluated 3 multilingual sub-types of the novel NLP language model, BERT and compared its’ performance to the conventional machine learning classification techniques. XLM was the top-performing BERT model with an accuracy of 67.31%. Random Forest with Term Frequency Vectorizer was the best the top-performing model out of all the traditional classification models with an accuracy of 63.59%.

show abstract

Bangla Document Classification Using Deep Recurrent Neural Network with BiLSTM

Rahman

Chakraborty

2021

Algorithms for Intelligent Systems

View full text Add to dashboard Cite

Investigating Lstm with k-Max Pooling for Text Classification

Cited by 8 publications

References 11 publications

Feature-enhanced text-inception model for Chinese long text classification

Feature-enhanced text-inception model for Chinese long text classification

<strong>Cooking is All About People: Comment Classification on Cookery Channels Using Bert and Classification Models (Malayalam-English Mix-Code)</strong>

Bangla Document Classification Using Deep Recurrent Neural Network with BiLSTM

Contact Info

Product

Resources

About