# Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Recurrent Neural Network

arXiv: https://arxiv.org/abs/1510.06168 · HTML: https://mlsanity.com/paper/1510.06168/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Oct 2015.

## Built on by (most cited first, 9 of 9)

- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [Detection of Hate Speech using BERT and Hate Speech Word Embedding with Deep Model](https://mlsanity.com/paper/2111.01515/) (2021)
- [Conformal prediction for text infilling and part-of-speech prediction](https://mlsanity.com/paper/2111.02592/) (2021)
- [Improving Classifier Training Efficiency for Automatic Cyberbullying Detection with Feature Density](https://mlsanity.com/paper/2111.01689/) (2021)
- [CoLI-Machine Learning Approaches for Code-mixed Language Identification at the Word Level in Kannada-English Texts](https://mlsanity.com/paper/2211.09847/) (2022)
- [Effective Transfer Learning for Low-Resource Natural Language Understanding](https://mlsanity.com/paper/2208.09180/) (2022)
- [Extracting chemical food safety hazards from the scientific literature automatically using large language models](https://mlsanity.com/paper/2405.15787/) (2024)
- [Generation Of Colors using Bidirectional Long Short Term Memory Networks](https://mlsanity.com/paper/2311.06542/) (2023)
- [GWPT: A Green Word-Embedding-based POS Tagger](https://mlsanity.com/paper/2401.07475/) (2024)

## Abstract (arXiv)

Bidirectional Long Short-Term Memory Recurrent Neural Network (BLSTM-RNN) has been shown to be very effective for tagging sequential data, e.g. speech utterances or handwritten documents. While word embedding has been demoed as a powerful representation for characterizing the statistical properties of natural language. In this study, we propose to use BLSTM-RNN with word embedding for part-of-speech (POS) tagging task. When tested on Penn Treebank WSJ test set, a state-of-the-art performance of 97.40 tagging accuracy is achieved. Without using morphological features, this approach can also achieve a good performance comparable with the Stanford POS tagger.