Comprehension Based Question Answering using Bloom’s Taxonomy
Pritish Sahu, Michael Cogswell, Ajay Divakaran, Sara Rutherford-Quach
Abstract
Current pre-trained language models have lots of knowledge, but a more limited ability to use that knowledge. Bloom’s Taxonomy helps educators teach children how to use knowledge by categorizing comprehension skills, so we use it to analyze and improve the comprehension skills of large pre-trained language models. Our experiments focus on zero-shot question answering, using the taxonomy to provide proximal context that helps the model answer questions by being relevant to those questions. We show targeting context in this manner improves performance across 4 popular common sense question answer datasets.- Anthology ID:
- 2021.repl4nlp-1.3
- Volume:
- Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021)
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Anna Rogers, Iacer Calixto, Ivan Vulić, Naomi Saphra, Nora Kassner, Oana-Maria Camburu, Trapit Bansal, Vered Shwartz
- Venue:
- RepL4NLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 20–28
- Language:
- URL:
- https://aclanthology.org/2021.repl4nlp-1.3
- DOI:
- 10.18653/v1/2021.repl4nlp-1.3
- Cite (ACL):
- Pritish Sahu, Michael Cogswell, Ajay Divakaran, and Sara Rutherford-Quach. 2021. Comprehension Based Question Answering using Bloom’s Taxonomy. In Proceedings of the 6th Workshop on Representation Learning for NLP (RepL4NLP-2021), pages 20–28, Online. Association for Computational Linguistics.
- Cite (Informal):
- Comprehension Based Question Answering using Bloom’s Taxonomy (Sahu et al., RepL4NLP 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2021.repl4nlp-1.3.pdf
- Data
- COPA, CommonsenseQA, WinoGrande