Skip to content
This repository has been archived by the owner on Dec 16, 2022. It is now read-only.

RoBERTa on SuperGLUE's 'Recognizing Textual Entailment' task #4999

Closed
dirkgr opened this issue Feb 18, 2021 · 1 comment
Closed

RoBERTa on SuperGLUE's 'Recognizing Textual Entailment' task #4999

dirkgr opened this issue Feb 18, 2021 · 1 comment
Assignees
Labels
Contributions welcome easy Tasks that are relatively easy. Models Issues related to the allennlp-models repo

Comments

@dirkgr
Copy link
Member

dirkgr commented Feb 18, 2021

RTE is one of the tasks of the SuperGLUE benchmark. The task is to re-trace the steps of Facebook's RoBERTa paper (https://arxiv.org/pdf/1907.11692.pdf) and build an AllenNLP config that reads the RTE data and fine-tunes a model on it. We expect scores in the range of their entry on the SuperGLUE leaderboard.

We recommend you use the AllenNLP Repository Template as a starting point. It might also be helpful to look at how the TransformerQA model works (training config, reader, model).

@dirkgr dirkgr added Good First Issue A great place to start for first time contributors Contributions welcome Models Issues related to the allennlp-models repo GSoC easy Tasks that are relatively easy. and removed Good First Issue A great place to start for first time contributors labels Feb 18, 2021
@dirkgr dirkgr removed the GSoC label Mar 9, 2021
@dirkgr
Copy link
Member Author

dirkgr commented Apr 16, 2021

Done!

@dirkgr dirkgr closed this as completed Apr 16, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
Contributions welcome easy Tasks that are relatively easy. Models Issues related to the allennlp-models repo
Projects
None yet
Development

No branches or pull requests

2 participants