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 2012.09938cs.CLcs.AI
收藏

Transformers能推理动作的效果吗?

Can Transformers Reason About Effects of Actions?

Arizona State University(亚利桑那州立大学);Microsoft(微软);New Mexico State University(新墨西哥州立大学)

Pratyay Banerjee, Chitta Baral, Man Luo, Arindam Mitra, Kuntal Pal, Tran C. Son, Neeraj Varshney

摘要:

最近的工作表明,Transformers能够“原因”的事实和规则在有限的设置,其中规则是自然语言表达式的条件连接暗示的结论。由于这表明,Transformers可以用于推理与自然语言的知识,我们做了严格的评估,这方面的一个共同的形式的知识和相应的推理-推理行动的影响。从人工智能的早期开始,关于动作和变化的推理一直是人工智能知识表示子领域的首要焦点,最近它已经成为常识问答的一个亮点。我们认为四个动作域(块世界,物流,码头工人机器人和通用域)在自然语言和创建QA数据集,涉及推理的影响,在这些领域的行动。我们调查的能力Transformers(a)学习在这些领域的原因和(b)转移,学习从通用域到其他域。

英文摘要:

A recent work has shown that transformers are able to "reason" with facts and rules in a limited setting where the rules are natural language expressions of conjunctions of conditions implying a conclusion. Since this suggests that transformers may be used for reasoning with knowledge given in natural language, we do a rigorous evaluation of this with respect to a common form of knowledge and its corresponding reasoning -- the reasoning about effects of actions. Reasoning about action and change has been a top focus in the knowledge representation subfield of AI from the early days of AI and more recently it has been a highlight aspect in common sense question answering. We consider four action domains (Blocks World, Logistics, Dock-Worker-Robots and a Generic Domain) in natural language and create QA datasets that involve reasoning about the effects of actions in these domains. We investigate the ability of transformers to (a) learn to reason in these domains and (b) transfer that learning from the generic domains to the other domains.

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。

↑