Chung-Ching Chang


2024

pdf bib
Memory Augmented Language Models through Mixture of Word Experts
Cicero Nogueira dos Santos | James Lee-Thorp | Isaac Noble | Chung-Ching Chang | David Uthus
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)

Scaling up the number of parameters of language models has proven to be an effective approach to improve performance. For dense models, increasing their size proportionally increases their computational footprint. In this work, we seek to aggressively decouple learning capacity and FLOPs through Mixture-of-Experts (MoE) style models with large knowledge-rich vocabulary based routing functions. Our proposed approach, dubbed Mixture of Word Experts (MoWE), can be seen as a memory augmented model, where a large set of word-specific experts play the role of a sparse memory. We demonstrate that MoWE performs significantly better than the T5 family of models with similar number of FLOPs in a variety of NLP tasks. Moreover, MoWE outperforms traditional MoE models on knowledge intensive tasks and has similar performance to complex memory augmented approaches that often require to invoke custom mechanisms to search the sparse memory.