Abductive reasoning aims at inferring the most plausible explanation for observed events, which would play critical roles in various NLP applications, such as reading comprehension and question answering. To facilitate this task, a narrative text based abductive reasoning task αNLI is proposed, together with explorations about building reasoning framework using pretrained language models. However, abundant event commonsense knowledge is not well exploited for this task. To fill this gap, we propose a variational autoencoder based model ege-RoBERTa, which employs a latent variable to capture the necessary commonsense knowledge from event graph for guiding the abductive reasoning task. Experimental results show that through learning the external event graph knowledge, our approach outperforms the baseline methods on the αNLI task.

Understanding event and event-centered commonsense reasoning are crucial for natural language processing (NLP). Given an observed event, it is trivial for human to infer its intents and effects, while this type of If-Then reasoning still remains challenging for NLP systems. To facilitate this, a If-Then commonsense reasoning dataset Atomic is proposed, together with an RNN-based Seq2Seq model to conduct such reasoning. However, two fundamental problems still need to be addressed: first, the intents of an event may be multiple, while the generations of RNN-based Seq2Seq models are always semantically close; second, external knowledge of the event background may be necessary for understanding events and conducting the If-Then reasoning. To address these issues, we propose a novel context-aware variational autoencoder effectively learning event background information to guide the If-Then reasoning. Experimental results show that our approach improves the accuracy and diversity of inferences compared with state-of-the-art baseline methods.

No abstract

No abstract

Component assignment problem is a common challenge of reliability optimization, which is a non-deterministic polynomial hard problem widely used in the linear consecutive k-out-of-n systems. In consideration of the advantages of quantum computing and importance measure, this article proposed a novel algorithm, which is Birnbaum importance-based quantum genetic algorithm, to improve the efficiency and accuracy for solving component assignment problem. First, the model of reliability optimization for linear consecutive k-out-of-n systems is established. Second, the detailed procedure of Birnbaum importance-based quantum genetic algorithm is introduced to solve the component assignment problem. Moreover, the effectiveness and the convergence of the quantum genetic algorithm, Birnbaum importance-based genetic local search, and Birnbaum importance-based quantum genetic algorithm is discussed through two comparative experiments. Finally, the case of production monitor systems is introduced to illustrate the effectiveness of Birnbaum importance-based quantum genetic algorithm comparing with the Birnbaum importance-based two-stage approach.