When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting

Abstract

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.

References in corpus (14)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Sequence to Sequence Learning with Neural Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Longformer: The Long-Document Transformer
• HOGWILD!: A Lock-Free Approach to Parallelizing Stochastic Gradient Descent
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Generating Long Sequences with Sparse Transformers
• Big Bird: Transformers for Longer Sequences
• Long Short-Term Memory-Networks for Machine Reading
• Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
• On the Turing Completeness of Modern Neural Network Architectures
• EDS-MEMBED: Multi-sense embeddings based on enhanced distributional semantic structures via a graph walk over word senses
• The exp-normal distribution is infinitely divisible