Parallel Iterative Edit Models for Local Sequence Transduction
This provides a faster alternative for local sequence transduction tasks, though it is incremental as it builds on existing encoder-decoder models by modifying the decoding approach.
The paper tackles the problem of slow sequential decoding in local sequence transduction tasks like grammatical error correction by proposing a Parallel Iterative Edit (PIE) model that performs parallel decoding, achieving competitive accuracy while being significantly faster.
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.