No abstract

Script event prediction involves building a model using recent event sequence records to capture the correlation between events and predict future ones. However, existing methods require a large amount of training data to perform well. In many real-world scenarios, labeled data is scarce and data distribution is uneven, making it challenging to achieve satisfactory performance. Additionally, the learning process of many models demands significant computational resources, which can render them unsuitable for low-resource settings. In order to fill the task blank of event prediction in low resource scenarios, a general framework called Meta-memory low resource network learning model(MLN) is proposed. Firstly, MLN captures the memory of events that occurred in the history through trend learner, learns the context-implied representation between events, and can predict future events based on the implied representation. Secondly, a Meta-memory predictor is proposed, which can further aggregate similar contextual implicit representations to form meta-memory representations, To realize the long-term memory learning process under the condition of few-shot. Finally, a gated network combination method combines the trend learner with the Meta-memory predictor to improve the effect of event prediction. We conducted experiments on four real data sets, and the results showed the effectiveness of MLN.

This paper proposes a new tactical decision aids method based on event knowledge graph (EventKG). In the warfare domain, EventKG can be constructed through event types design, event network construction and transition probability computation between events. Initially, four event classes are introduced in accordance with the OODA loop, and eighteen subclasses are further decomposed. With the aids of a common event template, all the events taking place in the battle field can be described. Event networks are built by adopting the hierarchical task network (HTN) and described through Bayesian network, to exhibit various relations between battle events. Transition probability, namely the occurrence probability of next possible event, is computed by using the prior probability and conditional probability of event occurring. On the basis of structured EventKG, entity knowledge graph (EKG) and entity relation knowledge graph (ERKG), tactical decision aid instructions can be generated by combining with the battlefield situation information.