OpenBookQA: A New Dataset for Advanced Question-Answering
Multi-step Reasoning, Commonsense Knowledge, and Rich Text Comprehension
Source
Huggingface Hub: link
About this dataset
OpenBookQA aims to promote research in advanced question-answering, probing a deeper understanding of both the topic (with salient facts summarized as an open book, also provided with the dataset) and the language it is expressed in. In particular, it contains questions that require multi-step reasoning, use of additional common and commonsense knowledge, and rich text comprehension. OpenBookQA is a new kind of question-answering dataset modeled after open book exams for assessing human understanding of a subject.
With OpenBookQA, we hope to push the boundaries of what current QA models can do and advance the state-of-the-art in this field. In addition to providing a challenging benchmark for existing models, we hope that this dataset will encourage new model architectures that can better handle complex questions and reasoning
How to use the dataset
Research Ideas
- Questions that require multi-step reasoning,
- Use of additional common and commonsense knowledge,
- Rich text comprehension
Acknowledgements
License
> License: CC0 1.0 Universal (CC0 1.0) - Public Domain Dedication
> No Copyright - You can copy, modify, distribute and perform the work, even for commercial purposes, all without asking permission. See Other Information.
Columns
File: main_test.csv
Column name |
Description |
question_stem |
The column 'question_stem' contains the stem of the question. (String) |
choices |
The column 'choices' contains a list of answers to choose from. (List) |
answerKey |
The column 'answerKey' contains the index of the correct answer in the choices list. (Integer) |
File: main_train.csv
Column name |
Description |
question_stem |
The column 'question_stem' contains the stem of the question. (String) |
choices |
The column 'choices' contains a list of answers to choose from. (List) |
answerKey |
The column 'answerKey' contains the index of the correct answer in the choices list. (Integer) |
File: additional_train.csv
Column name |
Description |
question_stem |
The column 'question_stem' contains the stem of the question. (String) |
choices |
The column 'choices' contains a list of answers to choose from. (List) |
answerKey |
The column 'answerKey' contains the index of the correct answer in the choices list. (Integer) |
File: additional_test.csv
Column name |
Description |
question_stem |
The column 'question_stem' contains the stem of the question. (String) |
choices |
The column 'choices' contains a list of answers to choose from. (List) |
answerKey |
The column 'answerKey' contains the index of the correct answer in the choices list. (Integer) |
File: additional_validation.csv
Column name |
Description |
question_stem |
The column 'question_stem' contains the stem of the question. (String) |
choices |
The column 'choices' contains a list of answers to choose from. (List) |
answerKey |
The column 'answerKey' contains the index of the correct answer in the choices list. (Integer) |
File: main_validation.csv
Column name |
Description |
question_stem |
The column 'question_stem' contains the stem of the question. (String) |
choices |
The column 'choices' contains a list of answers to choose from. (List) |
answerKey |
The column 'answerKey' contains the index of the correct answer in the choices list. (Integer) |