SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2111.09280 · 2021

Character Transformations for Non-Autoregressive GEC Tagging

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

We propose a character-based nonautoregressive GEC approach, with automatically generated character transformations. Recently, per-word classification of correction edits has proven an efficient, parallelizable alternative to current encoder-decoder GEC systems. We show that word replacement edits may be suboptimal and lead to explosion of rules for spelling, diacritization and errors in morphologically rich languages, and propose a method for generating character transformations from GEC corpus. Finally, we train character transformation models for Czech, German and Russian, reaching solid results and dramatic speedup compared to autoregressive systems. The source code is released at https://github.com/ufal/wnut2021_character_transformations_gec.

For agents

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

get_harvested_code_for_paper("2111.09280")
get_code_for_paper("2111.09280")
have("2111.09280")

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

curl https://syntology.ai/api/ran/2111.09280.json

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

[![Syntology run record](https://syntology.ai/api/ran/2111.09280.svg)](https://syntology.ai/paper/2111.09280)

Connect an agent — have() is free.