# Character Eyes: Seeing Language through Character-Level Taggers

arXiv: https://arxiv.org/abs/1903.05041 · HTML: https://mlsanity.com/paper/1903.05041/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2019.

## Built on by (most cited first, 3 of 3)

- [CANINE: Pre-training an Efficient Tokenization-Free Encoder for Language Representation](https://mlsanity.com/paper/2103.06874/) (2021)
- [Greed is All You Need: An Evaluation of Tokenizer Inference Methods](https://mlsanity.com/paper/2403.01289/) (2024)
- [A Vocabulary-Free Multilingual Neural Tokenizer for End-to-End Task Learning](https://mlsanity.com/paper/2204.10815/) (2022)

## Abstract (arXiv)

Character-level models have been used extensively in recent years in NLP tasks as both supplements and replacements for closed-vocabulary token-level word representations. In one popular architecture, character-level LSTMs are used to feed token representations into a sequence tagger predicting token-level annotations such as part-of-speech (POS) tags. In this work, we examine the behavior of POS taggers across languages from the perspective of individual hidden units within the character LSTM. We aggregate the behavior of these units into language-level metrics which quantify the challenges that taggers face on languages with different morphological properties, and identify links between synthesis and affixation preference and emergent behavior of the hidden tagger layer. In a comparative experiment, we show how modifying the balance between forward and backward hidden units affects model arrangement and performance in these types of languages.