Learning to Create and Reuse Words in Open-Vocabulary Neural Language Modeling

Abstract

Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution in that they can create word types not attested in the training corpus, they do not capture the "bursty" distribution of such words. In this paper, we augment a hierarchical LSTM language model that generates sequences of word tokens character by character with a caching mechanism that learns to reuse previously generated words. To validate our model we construct a new open-vocabulary language modeling corpus (the Multilingual Wikipedia Corpus, MWC) from comparable Wikipedia articles in 7 typologically diverse languages and demonstrate the effectiveness of our model across this range of languages.

arXiv commentACL 2017

References in corpus (6)

• Neural Architecture Search with Reinforcement Learning
• A Clockwork RNN
• Hierarchical Multiscale Recurrent Neural Networks
• Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations
• Recurrent Dropout without Memory Loss
• On Multiplicative Integration with Recurrent Neural Networks

Cited by in corpus (9)

• Maybe Deep Neural Networks are the Best Choice for Modeling Source Code
• Fast Parametric Learning with Activation Memorization
• Learning to Remember Translation History with a Continuous Cache
• Evaluating Online Continual Learning with CALM
• MultiFiT: Efficient Multi-lingual Language Model Fine-tuning
• Learning to Discover, Ground and Use Words with Segmental Neural Language Models
• 2kenize: Tying Subword Sequences for Chinese Script Conversion
• Are All Languages Equally Hard to Language-Model?
• Revisiting Neural Language Modelling with Syllables