Revise ACL paper error analysis in ChatGPT
Ground paper revisions in a linguistic task, a concrete input and output, counted errors, and the languages covered.
中文Install in ChatGPT
A ChatGPT workspace with skill creation enabled. Paste the fictional material below as text.
- In a ChatGPT workspace with skill creation enabled, open Plugins → Skills → Create → Create with editor.
- Create a skill in the editor and adapt the text-only `acl-writing-style` workflow from the pinned GitHub source into its instructions.
- Save the skill, then type @ in a new chat to select it and try the example.
Example task
Revise the opening and error analysis using this fictional Linden parser study.
study="Linden parser"; testedLanguage="Spanish"; testedExamples=60; errorBucket="negation scope"; bucketErrors=9; sampleInput="No todos vinieron"; gold="not all came"; baseline="none came"What to check
Show `No todos vinieron → not all came` beside the baseline error. State that there were 9 negation-scope errors in 60 Spanish examples and scope the finding to the given data and language.
Original SKILL.md on GitHub · Updated
Frequently asked question
How can ChatGPT check evidence for an ACL paper error example?
Show the input, expected output and failure. Link the example to the count for that error type and state the tested language.