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 2203.12186cs.CL
收藏

AbductionRules:训练Transformer以解释意外输入

AbductionRules: Training Transformers to Explain Unexpected Inputs

Strong AI Lab(强人工智能实验室);School of Computer Science(计算机学院);University of Auckland(奥克兰大学)

Nathan Young, Qiming Bao, Joshua Bensemann, Michael Witbrock

AI总结:

针对Transformer溯因推理研究不足的问题,该研究提出用于训练测试自然语言溯因能力的AbductionRules数据集,微调预训练Transformer后发现模型掌握可泛化溯因技巧也会利用数据结构,并探讨了方法可行性与改进方向。

摘要:

近期研究表明,Transformer能够可靠地对以自然语言表达的事实和规则执行逻辑推理,但溯因推理——即对意外观测结果推断最佳解释的推理方式——尚未得到充分研究,尽管它在科学发现、常识推理和模型可解释性方面有重要应用。我们提出了AbductionRules,这是一组用于训练和测试自然语言知识库上可泛化溯因能力的自然语言数据集。我们使用这些数据集微调预训练Transformer并讨论其性能,发现模型不仅学会了可泛化的溯因技巧,也学会了利用数据结构。最后,我们讨论了这种溯因推理方法的可行性以及未来工作中可能的改进方向。

英文摘要:

Transformers have recently been shown to be capable of reliably performing logical reasoning over facts and rules expressed in natural language, but abductive reasoning - inference to the best explanation of an unexpected observation - has been underexplored despite significant applications to scientific discovery, common-sense reasoning, and model interpretability. We present AbductionRules, a group of natural language datasets designed to train and test generalisable abduction over natural-language knowledge bases. We use these datasets to finetune pretrained Transformers and discuss their performance, finding that our models learned generalisable abductive techniques but also learned to exploit the structure of our data. Finally, we discuss the viability of this approach to abductive reasoning and ways in which it may be improved in future work.

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。

↑