arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1912.01110cs.CLcs.LGstat.ML
收藏

多语言代数数学应用题生成平台

A Multi-language Platform for Generating Algebraic Mathematical Word Problems

University of Moratuwa(莫拉图瓦大学)

Vijini Liyanage, Surangika Ranathunga

摘要:

现有的方法自动生成数学应用题被剥夺了定制性和创造性,由于其采用的基于模板的机制的固有性质。我们提出了一个解决这个问题的方法,使用深度神经语言生成机制。我们的方法使用字符级长短期记忆网络(LSTM)来生成单词问题,并使用POS(词性)标签来解决生成的问题中发现的约束。我们的方法能够生成英语和僧伽罗语的数学单词问题,准确率超过90%。

英文摘要:

Existing approaches for automatically generating mathematical word problems are deprived of customizability and creativity due to the inherent nature of template-based mechanisms they employ. We present a solution to this problem with the use of deep neural language generation mechanisms. Our approach uses a Character Level Long Short Term Memory Network (LSTM) to generate word problems, and uses POS (Part of Speech) tags to resolve the constraints found in the generated problems. Our approach is capable of generating Mathematics Word Problems in both English and Sinhala languages with an accuracy over 90%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑