# Character-Word LSTM Language Models

arXiv: https://arxiv.org/abs/1704.02813 · HTML: https://mlsanity.com/paper/1704.02813/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2017.

## Built on by (most cited first, 5 of 5)

- [One Small Step for Generative AI, One Giant Leap for AGI: A Complete Survey on ChatGPT in AIGC Era](https://mlsanity.com/paper/2304.06488/) (2023)
- [An Overview on Language Models: Recent Developments and Outlook](https://mlsanity.com/paper/2303.05759/) (2023)
- [Recent Trends in Named Entity Recognition (NER)](https://mlsanity.com/paper/2101.11420/) (2021)
- [SciEv: Finding Scientific Evidence Papers for Scientific News](https://mlsanity.com/paper/2205.00126/) (2022)
- [Differentiating Emigration from Return Migration of Scholars Using Name-Based Nationality Detection Models](https://mlsanity.com/paper/2505.06107/) (2025)

## Abstract (arXiv)

We present a Character-Word Long Short-Term Memory Language Model which both reduces the perplexity with respect to a baseline word-level language model and reduces the number of parameters of the model. Character information can reveal structural (dis)similarities between words and can even be used when a word is out-of-vocabulary, thus improving the modeling of infrequent and unknown words. By concatenating word and character embeddings, we achieve up to 2.77% relative improvement on English compared to a baseline model with a similar amount of parameters and 4.57% on Dutch. Moreover, we also outperform baseline word-level models with a larger number of parameters.