arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2109.03034cs.CLcs.AI
收藏

Generate & Rank:一个数学应用题的多任务框架

Generate & Rank: A Multi-task Framework for Math Word Problems

Huawei HiSilicon(华为海思);Peking University(北京大学)

Jianhao Shen, Yichun Yin, Lin Li, Lifeng Shang, Xin Jiang, Ming Zhang, Qun Liu

摘要:

数学应用题是自然语言处理中的一个具有挑战性和关键性的任务。最近的许多研究将MWP形式化为生成任务,并采用序列到序列模型将问题描述转换为数学表达式。然而,数学表达式容易出现小错误,而生成目标并不明确地处理这样的错误。为了解决这个问题,我们设计了一个新的排名任务MWP和提出生成&排名,一个多任务框架的基础上生成预训练的语言模型。通过与生成和排名的联合训练,模型从自己的错误中学习,并能够区分正确和不正确的表达。同时,我们执行专门为MWP设计的基于树的扰动和在线更新以提高排名。我们证明了我们提出的方法在基准测试中的有效性,结果表明,我们的方法在所有数据集中的性能始终优于基线。特别地,在经典的Math23 k中,我们的方法比最先进的方法高7%(78.4% $\rightarrow$ 85.4%)。

英文摘要:

Math word problem (MWP) is a challenging and critical task in natural language processing. Many recent studies formalize MWP as a generation task and have adopted sequence-to-sequence models to transform problem descriptions to mathematical expressions. However, mathematical expressions are prone to minor mistakes while the generation objective does not explicitly handle such mistakes. To address this limitation, we devise a new ranking task for MWP and propose Generate & Rank, a multi-task framework based on a generative pre-trained language model. By joint training with generation and ranking, the model learns from its own mistakes and is able to distinguish between correct and incorrect expressions. Meanwhile, we perform tree-based disturbance specially designed for MWP and an online update to boost the ranker. We demonstrate the effectiveness of our proposed method on the benchmark and the results show that our method consistently outperforms baselines in all datasets. Particularly, in the classical Math23k, our method is 7% (78.4% $\rightarrow$ 85.4%) higher than the state-of-the-art.

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。

↑