arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.10568cs.AIcs.CLcs.LG
收藏

具有奖励塑造的多跳知识图谱推理

Multi-Hop Knowledge Graph Reasoning with Reward Shaping

Salesforce Research(Salesforce研究院)

Xi Victoria Lin, Richard Socher, Caiming Xiong

摘要:

多跳推理是不完备知识图谱(KG)上的一种有效的查询回答(QA)方法。该问题可以用强化学习(RL)设置来表述,其中基于策略的代理顺序地扩展其推理路径,直到到达目标。然而,在一个不完整的KG环境中,代理收到低质量的奖励损坏的假阴性的训练数据,这损害了在测试时的泛化。此外,由于没有使用黄金动作序列进行训练,智能体可能会被虚假的搜索轨迹误导,从而偶然导致正确的答案。我们提出了两个建模改进来解决这两个问题:(1)我们通过采用预训练的一跳嵌入模型来估计未观察到的事实的奖励来减少假阴性监督的影响;(2)我们通过强制代理使用随机生成的边缘掩码探索不同的路径来对抗对策略RL的虚假路径的敏感性。我们的方法在几个基准数据集上显着改进了现有的基于路径的KGQA模型,并且与基于嵌入的模型相当或更好。

英文摘要:

Multi-hop reasoning is an effective approach for query answering (QA) over incomplete knowledge graphs (KGs). The problem can be formulated in a reinforcement learning (RL) setup, where a policy-based agent sequentially extends its inference path until it reaches a target. However, in an incomplete KG environment, the agent receives low-quality rewards corrupted by false negatives in the training data, which harms generalization at test time. Furthermore, since no golden action sequence is used for training, the agent can be misled by spurious search trajectories that incidentally lead to the correct answer. We propose two modeling advances to address both issues: (1) we reduce the impact of false negative supervision by adopting a pretrained one-hop embedding model to estimate the reward of unobserved facts; (2) we counter the sensitivity to spurious paths of on-policy RL by forcing the agent to explore a diverse set of paths using randomly generated edge masks. Our approach significantly improves over existing path-based KGQA models on several benchmark datasets and is comparable or better than embedding-based models.

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。

↑