Compositional Morphology for Word Representations and Language Modelling
This work addresses the challenge of handling large vocabularies and morphological complexity in language modeling and translation, offering a scalable solution for morphologically rich languages.
The paper tackles the problem of integrating compositional morphology into language models, resulting in substantial perplexity reductions and up to 1.2 BLEU point improvements in machine translation for morphologically rich languages.
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.