2019 ParallelIterativeEditModelsforL

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Parallel Iterative Edit (PIE) System, GEC Sequence Tagging System; Parallel Iterative Edit (PIE) Neural Network; Seq Edits Function; Local Sequence Transduction Task.

Notes

Cited By

Quotes

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 modeling 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.

References

BibTeX

@inproceedings{2019_ParallelIterativeEditModelsfor,
  author    = {Abhijeet Awasthi and
               Sunita Sarawagi and
               Rasna Goyal and
               Sabyasachi Ghosh and
               Vihari Piratla},
  editor    = {Kentaro Inui and
               Jing Jiang and
 [[Vincent Ng]] and
               Xiaojun Wan},
  title     = {Parallel Iterative Edit Models for Local Sequence Transduction},
  booktitle = {Proceedings of the 2019 Conference on Empirical Methods in Natural
               Language Processing and the 9th International Joint Conference on
               Natural Language Processing (EMNLP-IJCNLP 2019)},
  pages     = {4259--4269},
  publisher = {Association for Computational Linguistics},
  year      = {2019},
  url       = {https://doi.org/10.18653/v1/D19-1435},
  doi       = {10.18653/v1/D19-1435},
}


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2019 ParallelIterativeEditModelsforLAbhijeet Awasthi
Rasna Goyal
Sabyasachi Ghosh
Vihari Piratla
Sunita Sarawagi
Parallel Iterative Edit Models for Local Sequence Transduction2019