Abstract
We consider the problem of extracting from text commonsense knowledge pertaining to human senses such as sound and smell. First, we consider the problem of recognizing mentions of human senses in text. Our contribution is a method for acquiring labeled data. Experiments show the effectiveness of our proposed data labeling approach when used with standard machine learning models on the task of sense recognition in text. Second, we propose to extract novel, common sense relationships pertaining to sense perception concepts. Our contribution is a process for generating labeled data by leveraging large corpora and crowdsourcing questionnaires.- Anthology ID:
- D19-6005
- Volume:
- Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing
- Month:
- November
- Year:
- 2019
- Address:
- Hong Kong, China
- Editors:
- Simon Ostermann, Sheng Zhang, Michael Roth, Peter Clark
- Venue:
- WS
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 43–52
- Language:
- URL:
- https://aclanthology.org/D19-6005
- DOI:
- 10.18653/v1/D19-6005
- Cite (ACL):
- Ndapa Nakashole. 2019. Commonsense about Human Senses: Labeled Data Collection Processes. In Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing, pages 43–52, Hong Kong, China. Association for Computational Linguistics.
- Cite (Informal):
- Commonsense about Human Senses: Labeled Data Collection Processes (Nakashole, 2019)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/D19-6005.pdf