2020/02/11 by John Roberts Anderson, Qingqing Huang, Anderson, John +7
Computer Science · #Advanced Image and Video Retrieval Techniques #Caching and Content Delivery #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Topic Modeling
paper · pdf · doi:10.48550/arxiv.2002.04723
openalex publication_date 2020/02/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.