# Tabula nearly rasa: Probing the Linguistic Knowledge of Character-Level Neural Language Models Trained on Unsegmented Text

arXiv: https://arxiv.org/abs/1906.07285 · HTML: https://mlsanity.com/paper/1906.07285/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jun 2019.

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

- [From Babble to Words: Pre-Training Language Models on Continuous Streams of Phonemes](https://mlsanity.com/paper/2410.22906/) (2024)
- [Are word boundaries useful for unsupervised language learning?](https://mlsanity.com/paper/2210.02956/) (2022)
- [Small Language Models Also Work With Small Vocabularies: Probing the Linguistic Abilities of Grapheme- and Phoneme-Based Baby Llamas](https://mlsanity.com/paper/2410.01487/) (2024)
- [BabyLM's First Words: Word Segmentation as a Phonological Probing Task](https://mlsanity.com/paper/2504.03338/) (2025)
- [Why Do Neural Language Models Still Need Commonsense Knowledge to Handle Semantic Variations in Question Answering?](https://mlsanity.com/paper/2209.00599/) (2022)

## Abstract (arXiv)

Recurrent neural networks (RNNs) have reached striking performance in many natural language processing tasks. This has renewed interest in whether these generic sequence processing devices are inducing genuine linguistic knowledge. Nearly all current analytical studies, however, initialize the RNNs with a vocabulary of known words, and feed them tokenized input during training. We present a multi-lingual study of the linguistic knowledge encoded in RNNs trained as character-level language models, on input data with word boundaries removed. These networks face a tougher and more cognitively realistic task, having to discover any useful linguistic unit from scratch based on input statistics. The results show that our "near tabula rasa" RNNs are mostly able to solve morphological, syntactic and semantic tasks that intuitively presuppose word-level knowledge, and indeed they learned, to some extent, to track word boundaries. Our study opens the door to speculations about the necessity of an explicit, rigid word lexicon in language learning and usage.