No abstract

Multi-party dialogue machine reading comprehension (MRC) brings an unprecedented challenge due to the multiple speakers and the complex discourse linkages among speaker-aware utterances. The majority of current methods only consider the textual aspects of dialogue situations, and pay little attention to crucial speaker-aware cues. This prevents a model from capturing the speaker's intention and important discourse information for questions in a complex discourse relationship, leading to the model giving wrong answers. In this paper, we construct a dialogue logic graph module by the relational graph convolutional network (R-GCN) to structure the dialogue information, and design a speaker prediction task to enhance the ability to capture discourse logic. Additionally, we construct a key utterance information decoupling module that focuses on the key discourse information flow involve questions, and filters out noise information. Extensive experiments FriendsQA and Molweni show that our approach outperforms competitive baselines and current state-of-the-art models, especially when dealing with more rounds of dialogue and questions involving people, events and time.

poisoned by the edible fungus accident occurred frequently in recent years since that there were no effectively and quickly recognition methods for the wild fungus. To tackle the problem, a wild fungus classification algorithm based on a deep convolutional neural network(CNN), Residual Network(ResNet), is proposed in this paper. And then, an optimization method is proposed for network training. In order to verify the effectiveness of the model and optimization method, a wild fungus database, in total of 1280 images, is used in this paper. The experimental results show that the proposed algorithm can effectively complete the classification task of wild mushrooms, and the optimization algorithm proposed in this paper can also effectively improve the classification effect of the algorithm model.