COCO-LM
This repository contains the scripts for fine-tuning COCO-LM pretrained models on GLUE and SQuAD 2.0 benchmarks.
Paper: COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining
Overview
We provide the scripts in two versions, based on two widely-used open-source codebases, the Fairseq Library and the Huggingface Transformers Library. The two code versions are mostly equivalent in functionality, and you are free to use either of them. However, we note that the fairseq version is what we used in our experiments, and it will best reproduce the results in the paper; the huggingface version is implemented later to provide compatibility with the Huggingface Transformers Library, and may yield slightly different results.
Please follow the README files under the two directories for running the code.
GLUE Fine-Tuning Results
The General Language Understanding Evaluation (GLUE) benchmark is a collection of sentence- or sentence-pair language understanding tasks for evaluating and analyzing natural language understanding systems.
GLUE dev set results of COCO-LM base++ and large++ models are as follows (median of 5 different random seeds):
| Model | MNLI-m/mm | QQP | QNLI | SST-2 | CoLA | RTE | MRPC | STS-B | AVG |
|---|---|---|---|---|---|---|---|---|---|
| COCO-LM base++ | 90.2/90.0 | 92.2 | 94.2 | 94.6 | 67.3 | 87.4 | 91.2 | 91.8 | 88.6 |
| COCO-LM large++ | 91.4/91.6 | 92.8 | 95.7 | 96.9 | 73.9 | 91.0 | 92.2 | 92.7 | 90.8 |
GLUE test set results of COCO-LM base++ and large++ models are as follows (no ensemble, task-specific tricks, etc.):
| Model | MNLI-m/mm | QQP | QNLI | SST-2 | CoLA | RTE | MRPC | STS-B | AVG |
|---|---|---|---|---|---|---|---|---|---|
| COCO-LM base++ | 89.8/89.3 | 89.8 | 94.2 | 95.6 | 68.6 | 82.3 | 88.5 | 90.3 | 87.4 |
| COCO-LM large++ | 91.6/91.1 | 90.5 | 95.8 | 96.7 | 70.5 | 89.2 | 88.4 | 91.8 | 89.3 |
SQuAD 2.0 Fine-Tuning Results
Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span, from the corresponding reading passage, or the question might be unanswerable.
SQuAD 2.0 dev set results of COCO-LM base++ and large++ models are as follows (median of 5 different random seeds):
| Model | EM | F1 |
|---|---|---|
| COCO-LM base++ | 85.4 | 88.1 |
| COCO-LM large++ | 88.2 | 91.0 |
Citation
If you find the code and models useful for your research, please cite the following paper:
@inproceedings{meng2021cocolm,
title={{COCO-LM}: Correcting and contrasting text sequences for language model pretraining},
author={Meng, Yu and Xiong, Chenyan and Bajaj, Payal and Tiwary, Saurabh and Bennett, Paul and Han, Jiawei and Song, Xia},
booktitle={Conference on Neural Information Processing Systems},
year={2021}
}
Contributing
This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.
This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact [email protected] with any additional questions or comments.
20 Jul 29, 2022
133 Dec 29, 2022
![[ICLR 2022] Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators](https://github.com/microsoft/AMOS/raw/main/AMOS.png)
22 Sep 15, 2022
305 Dec 16, 2022
92 Jan 3, 2023
574 Jan 2, 2023
![[NAACL & ACL 2021] SapBERT: Self-alignment pretraining for BERT.](https://github.com/cambridgeltl/sapbert/raw/main/sapbert_front_graphs_v6.png?raw=true)
104 Dec 7, 2022
39 Jan 7, 2023
88 Nov 17, 2022
17 Jun 20, 2022
8 Apr 03, 2022
365 Jan 09, 2023
11 Sep 25, 2022
0 Aug 02, 2022
341 Dec 23, 2022
5 Jun 08, 2022
1 Sep 16, 2021
146 Dec 22, 2022
39 Dec 16, 2022
20.2k Jan 09, 2023
0 Feb 04, 2022
1 Nov 29, 2022
126 Jan 06, 2023
76 Jan 07, 2023
1.7k Jan 01, 2023
98 Sep 17, 2022
29 Dec 14, 2022
28 Aug 22, 2022