When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting
This work addresses the speed bottleneck in word representation models for NLP researchers, though it is incremental as it builds on existing positional models.
The paper tackled the inefficiency of the positional language model by proposing a constrained positional model that adapts sparse attention mechanisms, resulting in a model that trains twice as fast and outperforms the original on language modeling.
In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art performance on the intrinsic word analogy task. However, the positional model is not practically fast and it has never been evaluated on qualitative criteria or extrinsic tasks. We propose a constrained positional model, which adapts the sparse attention mechanism from neural machine translation to improve the speed of the positional model. We evaluate the positional and constrained positional models on three novel qualitative criteria and on language modeling. We show that the positional and constrained positional models contain interpretable information about the grammatical properties of words and outperform other shallow models on language modeling. We also show that our constrained model outperforms the positional model on language modeling and trains twice as fast.