SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1903.04167 · 2019

Partially Shuffling the Training Data to Improve Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Although SGD requires shuffling the training data between epochs, currently none of the word-level language modeling systems do this. Naively shuffling all sentences in the training data would not permit the model to learn inter-sentence dependencies. Here we present a method that partially shuffles the training data between epochs. This method makes each batch random, while keeping most sentence ordering intact. It achieves new state of the art results on word-level language modeling on both the Penn Treebank and WikiText-2 datasets.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1903.04167")
get_code_for_paper("1903.04167")
have("1903.04167")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1903.04167.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1903.04167.svg)](https://syntology.ai/paper/1903.04167)

Connect an agent — have() is free.