Vector-Vector-Matrix Architecture: A Novel Hardware-Aware Framework for Low-Latency Inference in NLP Applications

Abstract

Deep neural networks have become the standard approach to building reliable Natural Language Processing (NLP) applications, ranging from Neural Machine Translation (NMT) to dialogue systems. However, improving accuracy by increasing the model size requires a large number of hardware computations, which can slow down NLP applications significantly at inference time. To address this issue, we propose a novel vector-vector-matrix architecture (VVMA), which greatly reduces the latency at inference time for NMT. This architecture takes advantage of specialized hardware that has low-latency vector-vector operations and higher-latency vector-matrix operations. It also reduces the number of parameters and FLOPs for virtually all models that rely on efficient matrix multipliers without significantly impacting accuracy. We present empirical results suggesting that our framework can reduce the latency of sequence-to-sequence and Transformer models used for NMT by a factor of four. Finally, we show evidence suggesting that our VVMA extends to other domains, and we discuss novel hardware for its efficient use.

arXiv commentTo appear at the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP '20), November 16-20, 2020, NMT, AI accelerators, co-design, TPU, OPU, 10 pages, 3 figures, 4 tables

References in corpus (9)

• Sequence to Sequence Learning with Neural Networks
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Deep Learning with Coherent Nanophotonic Circuits
• Longformer: The Long-Document Transformer
• Compressing Neural Networks with the Hashing Trick
• Generating Long Sequences with Sparse Transformers
• Reformer: The Efficient Transformer
• Big Bird: Transformers for Longer Sequences
• A Survey on Methods and Theories of Quantized Neural Networks