Explicit Word Density Estimation for Language Modelling

TL;DR

This paper introduces a novel language modeling approach using NeuralODEs and continuous Normalizing Flows, addressing limitations of traditional models and achieving improved performance.

Contribution

It proposes a new family of language models based on NeuralODEs and continuous Normalizing Flows, enhancing expressiveness over traditional softmax-based models.

Findings

Improved language modeling performance over baselines

Demonstrated the effectiveness of NeuralODEs in NLP

Connected NeuralODEs with Normalizing Flows for better expressiveness

Abstract

Language Modelling has been a central part of Natural Language Processing for a very long time and in the past few years LSTM-based language models have been the go-to method for commercial language modeling. Recently, it has been shown that when looking at language modelling from a matrix factorization point of view, the final Softmax layer limits the expressiveness of the model, by putting an upper bound on the rank of the resulting matrix. Additionally, a new family of neural networks based called NeuralODEs, has been introduced as a continuous alternative to Residual Networks. Moreover, it has been shown that there is a connection between these models and Normalizing Flows. In this work we propose a new family of language models based on NeuralODEs and the continuous analogue of Normalizing Flows and manage to improve on some of the baselines.