Abstract
“数学文字题是一段能反映数学等式潜在逻辑的叙述性文本。成功的数学问题生成在语言生成和教育领域都具有广阔的应用前景。前人的工作大多需要人工标注的模板或关键词作为输入,且未考虑数学表达式本身的特点。本文提出了一种多任务联合训练的问题文本生成模型。我们设计了三个辅助任务,包括数字间关系抽取、数值排序和片段替换预测。他们与生成目标联合训练,用以监督解码器的学习,增强模型对运算逻辑和问题条件的感知能力。实验证明所提方法能有效提升生成的数学文字题的质量。”- Anthology ID:
- 2022.ccl-1.17
- Volume:
- Proceedings of the 21st Chinese National Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Nanchang, China
- Editors:
- Maosong Sun (孙茂松), Yang Liu (刘洋), Wanxiang Che (车万翔), Yang Feng (冯洋), Xipeng Qiu (邱锡鹏), Gaoqi Rao (饶高琦), Yubo Chen (陈玉博)
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 178–189
- Language:
- Chinese
- URL:
- https://aclanthology.org/2022.ccl-1.17
- DOI:
- Cite (ACL):
- Tianyang Cao, Xiaodan Xu, and Baobao Chang. 2022. 生成,推理与排序:基于多任务架构的数学文字题生成(Generating, Reasoning & Ranking: Multitask Learning Framework for Math Word Problem Generation). In Proceedings of the 21st Chinese National Conference on Computational Linguistics, pages 178–189, Nanchang, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 生成,推理与排序:基于多任务架构的数学文字题生成(Generating, Reasoning & Ranking: Multitask Learning Framework for Math Word Problem Generation) (Cao et al., CCL 2022)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2022.ccl-1.17.pdf