Irina Piontkovskaya, Sergey Nikolenko, Alexander Podolskiy, Konstantin Yakovlev
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.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Grammatical error correction (GEC) is an important NLP task that is currently usually solved with autoregressive sequence-tosequence models. However, approaches of this class are inherently slow due to one-byone token generation, so non-autoregressive alternatives are needed. In this work, we propose a novel non-autoregressive approach to GEC that decouples the architecture into a permutation network that outputs a self-attention weight matrix that can be used in beam search to find the best permutation of input tokens (with auxiliary ins tokens) and a decoder network based on a step-unrolled denoising autoencoder that fills in specific tokens. This allows us to find the token permutation after only one forward pass of the permutation network, avoiding autoregressive constructions. We show that the resulting network improves over previously known non-autoregressive methods for GEC and reaches the level of autoregressive methods that do not use language-specific synthetic data generation methods. Our results are supported by a comprehensive experimental validation on the ConLL-2014 and Write&Improve+LOCNESS datasets and an extensive ablation study that supports our architectural and algorithmic choices.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2311.08191")
get_code_for_paper("2311.08191")
have("2311.08191")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2311.08191.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2311.08191)
Connect an agent — have() is free.