# Sentence-State LSTM for Text Representation

arXiv: https://arxiv.org/abs/1805.02474 · HTML: https://mlsanity.com/paper/1805.02474/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2018.

## Built on by (most cited first, 22 of 22)

- [Graph Learning: A Survey](https://mlsanity.com/paper/2105.00696/) (2021)
- [Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction](https://mlsanity.com/paper/2112.15012/) (2021)
- [Exploring the Efficacy of Automatically Generated Counterfactuals for Sentiment Analysis](https://mlsanity.com/paper/2106.15231/) (2021)
- [Better Feature Integration for Named Entity Recognition](https://mlsanity.com/paper/2104.05316/) (2021)
- [Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review](https://mlsanity.com/paper/2303.06471/) (2023)
- [BERTifying Sinhala -- A Comprehensive Analysis of Pre-trained Language Models for Sinhala Text Classification](https://mlsanity.com/paper/2208.07864/) (2022)
- [InducT-GCN: Inductive Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/2206.00265/) (2022)
- [Enhance Long Text Understanding via Distilled Gist Detector from Abstractive Summarization](https://mlsanity.com/paper/2110.04741/) (2021)
- [Improving Graph-based Sentence Ordering with Iteratively Predicted Pairwise Orderings](https://mlsanity.com/paper/2110.06446/) (2021)
- [Graph-Based Multilingual Label Propagation for Low-Resource Part-of-Speech Tagging](https://mlsanity.com/paper/2210.09840/) (2022)
- [Improving Long Text Understanding with Knowledge Distilled from Summarization Model](https://mlsanity.com/paper/2405.04955/) (2024)
- [Locally-Contextual Nonlinear CRFs for Sequence Labeling](https://mlsanity.com/paper/2103.16210/) (2021)
- [Named entity recognition architecture combining contextual and global features](https://mlsanity.com/paper/2112.08033/) (2021)
- [Fine-grained Geolocation Prediction of Tweets with Human Machine Collaboration](https://mlsanity.com/paper/2106.13411/) (2021)
- [Pre-Training a Graph Recurrent Network for Language Representation](https://mlsanity.com/paper/2209.03834/) (2022)
- [Dual-State Capsule Networks for Text Classification](https://mlsanity.com/paper/2109.04762/) (2021)
- [KARL-Trans-NER: Knowledge Aware Representation Learning for Named Entity Recognition using Transformers](https://mlsanity.com/paper/2111.15436/) (2021)
- [Pruned Graph Neural Network for Short Story Ordering](https://mlsanity.com/paper/2203.06778/) (2022)
- [A Global Context Mechanism for Sequence Labeling](https://mlsanity.com/paper/2305.19928/) (2023)
- [An Explainable Neural Radiomic Sequence Model with Spatiotemporal Continuity for Quantifying 4DCT-based Pulmonary Ventilation](https://mlsanity.com/paper/2503.23898/) (2025)
- [LinguaSynth: Heterogeneous Linguistic Signals for News Classification](https://mlsanity.com/paper/2506.21848/) (2025)
- [AI-Assisted Authoring for Transparent, Data-Driven Documents](https://mlsanity.com/paper/2601.06027/) (2025)

## Abstract (arXiv)

Bi-directional LSTMs are a powerful tool for text representation. On the other hand, they have been shown to suffer various limitations due to their sequential nature. We investigate an alternative LSTM structure for encoding text, which consists of a parallel state for each word. Recurrent steps are used to perform local and global information exchange between words simultaneously, rather than incremental reading of a sequence of words. Results on various classification and sequence labelling benchmarks show that the proposed model has strong representation power, giving highly competitive performances compared to stacked BiLSTM models with similar parameter numbers.