将时序与关系知识融入序列分类，提升模型理解能力。
A Neuro-Symbolic Framework for Sequence Classification with Relational and Temporal Knowledge
- 设计神经符号框架，动态利用不同时刻的背景知识
- 在新基准上验证，神经符号方法显著优于纯神经模型
- 揭示现有神经符号方法在时序任务中的不足，适合研究者参考
神经符号人工智能的一个目标是利用背景知识提升学习任务性能。然而，现有大多数框架仅关注知识不随时间变化的简化场景，忽略了时间维度。本文研究更具挑战性的知识驱动序列分类问题，其中不同时间段需使用不同的知识，并可利用时序关系。实验评估对比了多阶段神经符号架构与纯神经架构，在新提出的基准框架上进行。结果表明该新设定具有挑战性，同时揭示了神经符号方法在时序任务中尚未被充分探索的缺陷，为未来研究提供了宝贵参考。
原文摘要 · Abstract (English)
One of the goals of neuro-symbolic artificial intelligence is to exploit background knowledge to improve the performance of learning tasks. However, most of the existing frameworks focus on the simplified scenario where knowledge does not change over time and does not cover the temporal dimension. In this work we consider the much more challenging problem of knowledge-driven sequence classification where different portions of knowledge must be employed at different timesteps, and temporal relations are available. Our experimental evaluation compares multi-stage neuro-symbolic and neural-only architectures, and it is conducted on a newly-introduced benchmarking framework. Results demonstrate the challenging nature of this novel setting, and also highlight under-explored shortcomings of neuro-symbolic methods, representing a precious reference for future research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。