Abstract
We propose the first lightly-supervised approach to scoring an argument’s persuasiveness. Key to our approach is the novel hypothesis that lightly-supervised persuasiveness scoring is possible by explicitly modeling the major errors that negatively impact persuasiveness. In an evaluation on a new annotated corpus of online debate arguments, our approach rivals its fully-supervised counterparts in performance by four scoring metrics when using only 10% of the available training instances.- Anthology ID:
- I17-1060
- Volume:
- Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
- Month:
- November
- Year:
- 2017
- Address:
- Taipei, Taiwan
- Editors:
- Greg Kondrak, Taro Watanabe
- Venue:
- IJCNLP
- SIG:
- Publisher:
- Asian Federation of Natural Language Processing
- Note:
- Pages:
- 594–604
- Language:
- URL:
- https://aclanthology.org/I17-1060
- DOI:
- Cite (ACL):
- Isaac Persing and Vincent Ng. 2017. Lightly-Supervised Modeling of Argument Persuasiveness. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 594–604, Taipei, Taiwan. Asian Federation of Natural Language Processing.
- Cite (Informal):
- Lightly-Supervised Modeling of Argument Persuasiveness (Persing & Ng, IJCNLP 2017)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-1/I17-1060.pdf