SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.14822 · ACL Findings · 2021

Effective Batching for Recurrent Neural Network Grammars

Hiroshi Noji, Yohei Oseki

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

As a language model that integrates traditional symbolic operations and flexible neural representations, recurrent neural network grammars (RNNGs) have attracted great attention from both scientific and engineering perspectives. However, RNNGs are known to be harder to scale due to the difficulty of batched training. In this paper, we propose effective batching for RNNGs, where every operation is computed in parallel with tensors across multiple sentences. Our PyTorch implementation effectively employs a GPU and achieves x6 speedup compared to the existing C++ DyNet implementation with model-independent auto-batching. Moreover, our batched RNNG also accelerates inference and achieves x20-150 speedup for beam search depending on beam sizes. Finally, we evaluate syntactic generalization performance of the scaled RNNG against the LSTM baseline, based on the large training data of 100M tokens from English Wikipedia and the broad-coverage targeted syntactic evaluation benchmark. 1

For agents

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

get_harvested_code_for_paper("2105.14822")
get_code_for_paper("2105.14822")
have("2105.14822")

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

curl https://syntology.ai/api/ran/2105.14822.json

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

[![Syntology run record](https://syntology.ai/api/ran/2105.14822.svg)](https://syntology.ai/paper/2105.14822)

Connect an agent — have() is free.