Compositional Morphology for Word Representations and Language Modelling

Abstract

This paper presents a scalable method for integrating compositional morphological representations into a vector-based probabilistic language model. Our approach is evaluated in the context of log-bilinear language models, rendered suitably efficient for implementation inside a machine translation decoder by factoring the vocabulary. We perform both intrinsic and extrinsic evaluations, presenting results on a range of languages which demonstrate that our model learns morphological representations that both perform well on word similarity tasks and lead to substantial reductions in perplexity. When used for translation into morphologically rich languages with large vocabularies, our models obtain improvements of up to 1.2 BLEU points relative to a baseline system using back-off n-gram models.

Proceedings of the 31st International Conference on Machine Learning (ICML)

Cited by in corpus (6)

• LightRNN: Memory and Computation-Efficient Recurrent Neural Networks
• Learning Latent Local Conversation Modes for Predicting Community Endorsement in Online Discussions
• Using Interlinear Glosses as Pivot in Low-Resource Multilingual Machine Translation
• Gating Mechanisms for Combining Character and Word-level Word Representations: An Empirical Study
• Comparison of Turkish Word Representations Trained on Different Morphological Forms
• Stem-driven Language Models for Morphologically Rich Languages