2017 AutomaticAnnotationandEvaluatio

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Grammatical Error Correction, Text Error Correction System, Grammatical Error Annotation Toolkit (ERRANT).

Notes

Cited By

Quotes

Abstract

Until now, error type performance for Grammatical Error Correction (GEC) systems could only be measured in terms of recall because system output is not annotated. To overcome this problem, we introduce ERRANT, a grammatical ERRor Annotation Toolkit designed to automatically extract edits from parallel original and corrected sentences and classify them according to a new, dataset-agnostic, rule-based framework. This not only facilitates error type evaluation at different levels of granularity, but can also be used to reduce annotator workload and standardise existing GEC datasets. Human experts rated the automatic edits as "Good" or "Acceptable" in at least 95\% of cases, so we applied ERRANT to the system output of the CoNLL-2014 shared task to carry out a detailed error type analysis for the first time.

References

BibTeX

@inproceedings{bryant-etal-2017-automatic,
  author    = { Christopher Bryant and
               [[Mariano Felice]] and
               [[Ted Briscoe]]},
  title     = {Automatic Annotation and Evaluation of Error Types for Grammatical
               Error Correction},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational
               Linguistics, {ACL} 2017, Vancouver, Canada, July 30 - August 4, Volume
               1: Long Papers},
  pages     = {793--805},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  url       = {https://www.aclweb.org/anthology/P17-1074},
  doi       = {10.18653/v1/P17-1074},
}


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2017 AutomaticAnnotationandEvaluatioTed Briscoe
Christopher Bryant
Mariano Felice
Automatic Annotation and Evaluation of Error Types for Grammatical Error Correction2017