Tabula nearly rasa: Probing the Linguistic Knowledge of Character-Level Neural Language Models Trained on Unsegmented Text
arXiv:1906.07285
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.
arXiv commentAccepted by Transactions of the Association for Computational Linguistics
References in corpus (8)
- Efficient Estimation of Word Representations in Vector Space
- Sequence to Sequence Learning with Neural Networks
- Character-Aware Neural Language Models
- Learning to Generate Reviews and Discovering Sentiment
- What do Neural Machine Translation Models Learn about Morphology?
- An Analysis of Neural Language Modeling at Multiple Scales
- Unsupervised word segmentation and lexicon discovery using acoustic word embeddings
- Alternative structures for character-level RNNs