# Text Classification Improved by Integrating Bidirectional LSTM with Two-dimensional Max Pooling

arXiv: https://arxiv.org/abs/1611.06639 · HTML: https://mlsanity.com/paper/1611.06639/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Nov 2016.

## Built on by (most cited first, 30 of 39)

- [AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing](https://mlsanity.com/paper/2108.05542/) (2021)
- [Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs](https://mlsanity.com/paper/2108.13873/) (2021)
- [Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP](https://mlsanity.com/paper/2109.03777/) (2021)
- [InducT-GCN: Inductive Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2206.00265/) (2022)
- [Does Head Label Help for Long-Tailed Multi-Label Text Classification](https://mlsanity.com/paper/2101.09704/) (2021)
- [SA2SL: From Aspect-Based Sentiment Analysis to Social Listening System for Business Intelligence](https://mlsanity.com/paper/2105.15079/) (2021)
- [DialogueBERT: A Self-Supervised Learning based Dialogue Pre-training Encoder](https://mlsanity.com/paper/2109.10480/) (2021)
- [A Multi-task Model for Sentiment Aided Stance Detection of Climate Change Tweets](https://mlsanity.com/paper/2211.03533/) (2022)
- [Weakly Supervised Text Classification using Supervision Signals from a Language Model](https://mlsanity.com/paper/2205.06604/) (2022)
- [Cyberbullying Detection for Low-resource Languages and Dialects: Review of the State of the Art](https://mlsanity.com/paper/2308.15745/) (2023)
- [Exploring deep learning methods for recognizing rare diseases and their clinical manifestations from texts](https://mlsanity.com/paper/2109.00343/) (2021)
- [Identifying Illicit Drug Dealers on Instagram with Large-scale Multimodal Data Fusion](https://mlsanity.com/paper/2108.08301/) (2021)
- [TUDublin team at Constraint@AAAI2021 -- COVID19 Fake News Detection](https://mlsanity.com/paper/2101.05701/) (2021)
- [Large-Scale News Classification using BERT Language Model: Spark NLP Approach](https://mlsanity.com/paper/2107.06785/) (2021)
- [Navigating the Kaleidoscope of COVID-19 Misinformation Using Deep Learning](https://mlsanity.com/paper/2110.15703/) (2021)
- [Sentiment Analysis on Brazilian Portuguese User Reviews](https://mlsanity.com/paper/2112.05459/) (2021)
- [Embedding generation for text classification of Brazilian Portuguese user reviews: from bag-of-words to transformers](https://mlsanity.com/paper/2212.00587/) (2022)
- [Human Activity Recognition using Deep Learning Models on Smartphones and Smartwatches Sensor Data](https://mlsanity.com/paper/2103.03836/) (2021)
- [ReinforceBug: A Framework to Generate Adversarial Textual Examples](https://mlsanity.com/paper/2103.08306/) (2021)
- [Are We Really Making Much Progress in Text Classification? A Comparative Review](https://mlsanity.com/paper/2204.03954/) (2022)
- [MGIMN: Multi-Grained Interactive Matching Network for Few-shot Text Classification](https://mlsanity.com/paper/2204.04952/) (2022)
- [An Embarrassingly Simple Approach for Intellectual Property Rights Protection on Recurrent Neural Networks](https://mlsanity.com/paper/2210.00743/) (2022)
- [Attention is Not Always What You Need: Towards Efficient Classification of Domain-Specific Text](https://mlsanity.com/paper/2303.17786/) (2023)
- [Text Classification using Graph Convolutional Networks: A Comprehensive Survey](https://mlsanity.com/paper/2410.09399/) (2024)
- [ExBigBang: A Dynamic Approach for Explainable Persona Classification through Contextualized Hybrid Transformer Analysis](https://mlsanity.com/paper/2508.15364/) (2025)
- [Classifying several dialectal Nawatl varieties](https://mlsanity.com/paper/2601.02303/) (2026)
- [ReINTEL Challenge 2020: Exploiting Transfer Learning Models for Reliable Intelligence Identification on Vietnamese Social Network Sites](https://mlsanity.com/paper/2102.10794/) (2021)
- [Sentiment and Emotion Classification of Epidemic Related Bilingual data from Social Media](https://mlsanity.com/paper/2105.01468/) (2021)
- [New Arabic Medical Dataset for Diseases Classification](https://mlsanity.com/paper/2106.15236/) (2021)
- [LAME: Layout Aware Metadata Extraction Approach for Research Articles](https://mlsanity.com/paper/2112.12353/) (2021)

## Abstract (arXiv)

Recurrent Neural Network (RNN) is one of the most popular architectures used in Natural Language Processsing (NLP) tasks because its recurrent structure is very suitable to process variable-length text. RNN can utilize distributed representations of words by first converting the tokens comprising each text into vectors, which form a matrix. And this matrix includes two dimensions: the time-step dimension and the feature vector dimension. Then most existing models usually utilize one-dimensional (1D) max pooling operation or attention-based operation only on the time-step dimension to obtain a fixed-length vector. However, the features on the feature vector dimension are not mutually independent, and simply applying 1D pooling operation over the time-step dimension independently may destroy the structure of the feature representation. On the other hand, applying two-dimensional (2D) pooling operation over the two dimensions may sample more meaningful features for sequence modeling tasks. To integrate the features on both dimensions of the matrix, this paper explores applying 2D max pooling operation to obtain a fixed-length representation of the text. This paper also utilizes 2D convolution to sample more meaningful information of the matrix. Experiments are conducted on six text classification tasks, including sentiment analysis, question classification, subjectivity classification and newsgroup classification. Compared with the state-of-the-art models, the proposed models achieve excellent performance on 4 out of 6 tasks. Specifically, one of the proposed models achieves highest accuracy on Stanford Sentiment Treebank binary classification and fine-grained classification tasks.