# Charagram: Embedding Words and Sentences via Character n-grams

arXiv: https://arxiv.org/abs/1607.02789 · HTML: https://mlsanity.com/paper/1607.02789/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2016.

## Built on by (most cited first, 14 of 14)

- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [Dynamic Language Models for Continuously Evolving Content](https://mlsanity.com/paper/2106.06297/) (2021)
- [Text Rendering Strategies for Pixel Language Models](https://mlsanity.com/paper/2311.00522/) (2023)
- [Large Language Models Lack Understanding of Character Composition of Words](https://mlsanity.com/paper/2405.11357/) (2024)
- [Paraphrastic Representations at Scale](https://mlsanity.com/paper/2104.15114/) (2021)
- [Imputing Out-of-Vocabulary Embeddings with LOVE Makes Language Models Robust with Little Cost](https://mlsanity.com/paper/2203.07860/) (2022)
- [Evaluating Neural Word Embeddings for Sanskrit](https://mlsanity.com/paper/2104.00270/) (2021)
- [SanskritShala: A Neural Sanskrit NLP Toolkit with Web-Based Interface for Pedagogical and Annotation Purposes](https://mlsanity.com/paper/2302.09527/) (2023)
- [Integrating Approaches to Word Representation](https://mlsanity.com/paper/2109.04876/) (2021)
- [Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling](https://mlsanity.com/paper/2101.11889/) (2021)
- [Linguistically-Informed Neural Architectures for Lexical, Syntactic and Semantic Tasks in Sanskrit](https://mlsanity.com/paper/2308.08807/) (2023)
- [1Cademy at Semeval-2022 Task 1: Investigating the Effectiveness of Multilingual, Multitask, and Language-Agnostic Tricks for the Reverse Dictionary Task](https://mlsanity.com/paper/2206.03702/) (2022)
- [Efficient Entity Candidate Generation for Low-Resource Languages](https://mlsanity.com/paper/2206.15163/) (2022)
- [Handling Korean Out-of-Vocabulary Words with Phoneme Representation Learning](https://mlsanity.com/paper/2507.04018/) (2025)

## Abstract (arXiv)

We present Charagram embeddings, a simple approach for learning character-based compositional models to embed textual sequences. A word or sentence is represented using a character n-gram count vector, followed by a single nonlinear transformation to yield a low-dimensional embedding. We use three tasks for evaluation: word similarity, sentence similarity, and part-of-speech tagging. We demonstrate that Charagram embeddings outperform more complex architectures based on character-level recurrent and convolutional neural networks, achieving new state-of-the-art performance on several similarity tasks.