Keyword-to-caption reproducibility
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 2.3k
- Forks
- 213
- PR merge metrics
- No merged PRs in 30d
Description
Hey authors,
Thank you for the effort you put in publishing the code and answering questions.
Following your answer in #58 I attempted to replicate the examples you showed in appendix F in your paper with the package you referenced gagan3012/keytotext.
I went through all the models they specify in the documentation ('k2t-base', 'k2t', 'k2t-new', 'k2t-tiny', 'mrm8488/t5-base-finetuned-common_gen'), but none gave the results given in the column T5_raw_sentence for the input given in the column Keywords.
- Could you please elaborate on how you used the code for the K2C augmentation?
Thank you
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with appendix F, the response in issue #58, and the keytotext documentation. Compare the listed models and the Keywords inputs against the T5_raw_sentence column, then determine what exact K2C augmentation procedure was used. Done means the reproduction steps and expected outputs are explained clearly enough to account for the discrepancy.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 30/100