FastFusionNet: New State-of-the-Art for DAWNBench SQuAD

arxiv: 1902.11291 · v2 · pith:FHMYSEEDnew · submitted 2019-02-28 · 💻 cs.CL

FastFusionNet: New State-of-the-Art for DAWNBench SQuAD

Felix Wu , Boyi Li , Lequn Wang , Ni Lao , John Blitzer , Kilian Q. Weinberger This is my paper

classification 💻 cs.CL

keywords fastfusionnetarchitecturedawnbenchefficientfusionnetlayerssquadstate-of-the-art

0 comments p. Extension

pith:FHMYSEED Add to your LaTeX paper

What is a Pith Number?

\usepackage{pith}
\pithnumber{FHMYSEED}

Prints a linked pith:FHMYSEED badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

In this technical report, we introduce FastFusionNet, an efficient variant of FusionNet [12]. FusionNet is a high performing reading comprehension architecture, which was designed primarily for maximum retrieval accuracy with less regard towards computational requirements. For FastFusionNets we remove the expensive CoVe layers [21] and substitute the BiLSTMs with far more efficient SRU layers [19]. The resulting architecture obtains state-of-the-art results on DAWNBench [5] while achieving the lowest training and inference time on SQuAD [25] to-date. The code is available at https://github.com/felixgwu/FastFusionNet.

This paper has not been read by Pith yet.

FastFusionNet: New State-of-the-Art for DAWNBench SQuAD

discussion (0)