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

## TL;DR

This study investigates how character-level RNNs trained on unsegmented text can learn linguistic structures, revealing their ability to acquire morphological, syntactic, and semantic knowledge without explicit word boundaries.

## Contribution

It demonstrates that character-level RNNs trained without explicit word boundaries can still learn complex linguistic features, challenging the necessity of a predefined vocabulary.

## Key findings

- RNNs can learn morphological, syntactic, and semantic tasks from unsegmented text.
- They can partially discover word boundaries during training.
- Models perform well despite the lack of explicit word-level input.

## Abstract

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.