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 2007.07629cs.AIcs.LG
收藏

面向抽象论证语义的深度学习

Deep Learning for Abstract Argumentation Semantics

National Police Lab AI, Netherlands Police(荷兰警察局人工智能实验室);Utrecht University(乌得勒支大学);Tilburg University(蒂尔堡大学)

Dennis Craandijk, Floris Bex

摘要:

在本文中,我们提出了一个基于学习的方法来确定接受的论点下几个抽象的论证语义。更具体地说,我们提出了一个论证图神经网络(AGNN),学习消息传递算法来预测参数被接受的可能性。实验结果表明,AGNN几乎可以完美地预测不同语义和规模下的可接受性,以及更大的论证框架。此外,分析的消息传递算法的行为表明,AGNN学习坚持基本原则的参数语义在文献中确定,因此可以训练预测扩展不同的语义-我们展示了后者如何可以做多扩展语义使用AGNN指导基本搜索。我们在https://github.com/DennisCraandijk/DL-Abstract-Argumentation上发布代码

英文摘要:

In this paper, we present a learning-based approach to determining acceptance of arguments under several abstract argumentation semantics. More specifically, we propose an argumentation graph neural network (AGNN) that learns a message-passing algorithm to predict the likelihood of an argument being accepted. The experimental results demonstrate that the AGNN can almost perfectly predict the acceptability under different semantics and scales well for larger argumentation frameworks. Furthermore, analysing the behaviour of the message-passing algorithm shows that the AGNN learns to adhere to basic principles of argument semantics as identified in the literature, and can thus be trained to predict extensions under the different semantics - we show how the latter can be done for multi-extension semantics by using AGNNs to guide a basic search. We publish our code at https://github.com/DennisCraandijk/DL-Abstract-Argumentation

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。

↑