Superbloom: Bloom filter meets Transformer
arXiv:2002.04723
Abstract
We extend the idea of word pieces in natural language models to machine learning tasks on opaque ids. This is achieved by applying hash functions to map each id to multiple hash tokens in a much smaller space, similarly to a Bloom filter. We show that by applying a multi-layer Transformer to these Bloom filter digests, we are able to obtain models with high accuracy. They outperform models of a similar size without hashing and, to a large degree, models of a much larger size trained using sampled softmax with the same computational budget. Our key observation is that it is important to use a multi-layer Transformer for Bloom filter digests to remove ambiguity in the hashed input. We believe this provides an alternative method to solving problems with large vocabulary size.
References in corpus (6)
- Adam: A Method for Stochastic Optimization
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
- ERNIE: Enhanced Language Representation with Informative Entities
- Next Item Recommendation with Self-Attention
- Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations