Parallel Iterative Edit Models for Local Sequence Transduction

TL;DR

The paper introduces the Parallel Iterative Edit (PIE) model for local sequence transduction tasks, offering a faster alternative to traditional encoder-decoder models while maintaining competitive accuracy through iterative refinement and label prediction.

Contribution

The PIE model enables parallel decoding in local sequence transduction, combining iterative refinement and label prediction to achieve speed and accuracy improvements over encoder-decoder models.

Findings

PIE achieves accuracy comparable to encoder-decoder models.

PIE significantly reduces decoding time.

Effective across GEC, OCR, and spell correction tasks.

Abstract

We present a Parallel Iterative Edit (PIE) model for the problem of local sequence transduction arising in tasks like Grammatical error correction (GEC). Recent approaches are based on the popular encoder-decoder (ED) model for sequence to sequence learning. The ED model auto-regressively captures full dependency among output tokens but is slow due to sequential decoding. The PIE model does parallel decoding, giving up the advantage of modelling full dependency in the output, yet it achieves accuracy competitive with the ED model for four reasons: 1.~predicting edits instead of tokens, 2.~labeling sequences instead of generating sequences, 3.~iteratively refining predictions to capture dependencies, and 4.~factorizing logits over edits and their token argument to harness pre-trained language models like BERT. Experiments on tasks spanning GEC, OCR correction and spell correction demonstrate that the PIE model is an accurate and significantly faster alternative for local sequence transduction.