LATE Ain'T Earley: A Faster Parallel Earley Parser

TL;DR

The paper introduces the LATE algorithm, an asynchronous parallel version of the Earley parser, enabling significant speedups in parsing tasks by overcoming dependency challenges through new data structures.

Contribution

It presents the LATE algorithm, a novel asynchronous parallelization method for the Earley parser that allows task-independent processing and achieves substantial speedup.

Findings

Achieves up to 120x speedup over traditional Earley parser

Uses additional data structures to enable task parallelism

Effective on natural language parsing tasks

Abstract

We present the LATE algorithm, an asynchronous variant of the Earley algorithm for parsing context-free grammars. The Earley algorithm is naturally task-based, but is difficult to parallelize because of dependencies between the tasks. We present the LATE algorithm, which uses additional data structures to maintain information about the state of the parse so that work items may be processed in any order. This property allows the LATE algorithm to be sped up using task parallelism. We show that the LATE algorithm can achieve a 120x speedup over the Earley algorithm on a natural language task.