wyu97 / raco Goto Github PK

• This is the official resources of our EMNLP 2022 paper "Retrieval Augmentation for Commonsense Reasoning: A Unified Approach" [arXiv].

• Corpus (20M): Google drive [link]

• Code: Official DPR code [link]

  • first run python merge-corpus.py to construct corpus
  • modify the retrieval corpus path in above the DPR code

• Training Data: Google drive [link]

• Code: Official DPR code, same as above.

  • modify the training data path as

  raco_train:
      _target_: dpr.data.biencoder_data.JsonQADataset
      file: {your folder path}/train.json
  
  raco_dev:
      _target_: dpr.data.biencoder_data.JsonQADataset
      file: {your folder path}/dev.json
  

• Inference Data: Google drive [link]

• Code: Official DPR code, same as above.

  • modify the inference data path as

  {dataset}_train:
      _target_: dpr.data.retriever_data.CsvQASrc
      file: {your folder path}/{dataset}/train.tsv
  
  {dataset}_dev:
      _target_: dpr.data.retriever_data.CsvQASrc
      file: {your folder path}/{dataset}/dev.tsv
  
  {dataset}_test:
      _target_: dpr.data.retriever_data.CsvQASrc
      file: {your folder path}/{dataset}/test.tsv
  

• Training Data: obtained from the last step

• Code: Official FiD code [link]

• Accuracy is the same as exact match in FiD code.

• BLUE, ROUGE is from the CommonGen GitHub repo.

  • Some commonly seen issues when installing the lib [link]

@inproceedings{yu2022retrieval,
  title={Retrieval Augmentation for Commonsense Reasoning: A Unified Approach},
  author={Yu, Wenhao and Zhu, Chenguang and Zhang, Zhihan and Wang, Shuohang and Zhang, Zhuosheng and Fang, Yuwei and Jiang, Meng},
  booktitle={Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year={2022}
}

Please kindly cite our paper if you find this paper and the codes helpful.