Shallow GM-RKB WikiText Error Correction (WikiErrCorr) Task

A Shallow GM-RKB WikiText Error Correction (WikiErrCorr) Task is a automated GM-RKB editing task that is a shallow WikiText error correction task (required to repair WikiText errors in GM-RKB pages).

• Context:
  • It can be solved by a Shallow GM-RKB Error Correction System, such as GM-RKB WikiFixer.
  • …
• Example(s):
  • manually repair the erroneous fixes made by GM-RKB WikiFixer's System.
  • evaluate your performance against a GM-RKB Snapshot.
  • WikiErrCorr(“ the [[error] was ”) ⇒ “ the [[error]] was ".
  • WikiErrCorr(“ the <B>Bold text<b> was ”) ⇒ “ the <B>Bold text</B> was ".
  • …
• Counter-Example(s):
  • a Deep GM-RKB Error Repair Task, such as merging two nearly duplicate pages.
  • a GM-RKB Markup Addition Task.
  • a Automated Software Code Correction Task.
• See: WikiFixer Tool, Character String Processing.

---

---

References

2020

• (Melli et al., 2020) ⇒ Gabor Melli, Abdelrhman Eldallal, Bassim Lazem, and Olga Moreira (2020). “GM-RKB WikiText Error Correction Task and Baselines.”. In: Proceedings of the 12th Language Resources and Evaluation Conference (LREC-2020).
  • QUOTE: We designed and implemented the GM-RKB WikiText Error Correction (WEC) Task to benchmark systems that attempt to automatically recognize and repair simple typographical errors in WikiText based on frequent patterns observed in the corpus. The task consisted in conducting a series experiments on benchmark datasets to find the best performing WEC system. ...

2019

• (Melli et al., 2019) ⇒ GM-RKB WikiText Error Correction Task (LREC-2020).URL: https://github.com/GM-RKB/LREC-2020.
  • QUOTE: GM-RKB WikiText Error Correction Task goal is to benchmark systems that attempt to automatically detect and fix simple typographical errors in WikiText (Wiki Pages).

    This repository contains three different datasets used for evaluation, two different models used to fix Wiki pages, along with different tools and test scripts.

---