Abstract
道德词典资源的建设是人工智能伦理计算的一个研究重点。由于道德行为复杂多样,现有的英文道德词典分类体系并不完善,而中文方面目前尚未有相关的词典资源,理论体系和构建方法仍待探究。针对以上问题,该文提出了面向人工智能伦理计算的中文道德词典构建任务,设计了四类标签和四种类型,得到包含25,012个词的中文道德词典资源。实验结果表明,该词典资源不仅能够使机器学会道德知识,判断词的道德标签和类型,而且能够为句子级别的道德文本分析提供数据支持。- Anthology ID:
- 2020.ccl-1.50
- Volume:
- Proceedings of the 19th Chinese National Conference on Computational Linguistics
- Month:
- October
- Year:
- 2020
- Address:
- Haikou, China
- Editors:
- Maosong Sun (孙茂松), Sujian Li (李素建), Yue Zhang (张岳), Yang Liu (刘洋)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 539–549
- Language:
- Chinese
- URL:
- https://aclanthology.org/2020.ccl-1.50
- DOI:
- Cite (ACL):
- Hongrui Wang, Chang Liu, and Dong Yu. 2020. 面向人工智能伦理计算的中文道德词典构建方法研究(Construction of a Chinese Moral Dictionary for Artificial Intelligence Ethical Computing). In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 539–549, Haikou, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 面向人工智能伦理计算的中文道德词典构建方法研究(Construction of a Chinese Moral Dictionary for Artificial Intelligence Ethical Computing) (Wang et al., CCL 2020)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2020.ccl-1.50.pdf