TAT-QA
TAT-QA copied to clipboard
NExTplusplus
TAT-QA (Tabular And Textual dataset for Question Answering) contains 16,552 questions associated with 2,757 hybrid contexts from real-world financial reports.
hi, guys👋 Could you please upload the dataset to HuggingFace so that it can be easily downloaded?😊
Should the evaluation set use tatqa_dataset_dev.json or tatqa_dataset_test.json? In the submission section of https://nextplusplus.github.io/TAT-DQA/, the script: python tatqa_eval.py --gold_path=:path_to_dev --pred_path=:path_to_predictions seems to use the dev dataset for evaluation. Additionally, the...
Question `"uid": "c91ad938-6ad1-4481-8f6b-43ccd2f69926"` in the `tatqa_dataset_dev.json` appears to be annotated incorrectly. It's annotated as: ``` { "uid": "c91ad938-6ad1-4481-8f6b-43ccd2f69926", "order": 4, "question": "What is the nominal difference for ROFE between F19...
Metadata
Owner
Metadata
TAT-QA (Tabular And Textual dataset for Question Answering) contains 16,552 questions associated with 2,757 hybrid contexts from real-world financial reports.