Titlebook: Natural Language Processing and Chinese Computing; 8th CCF Internationa Jie Tang,Min-Yen Kan,Hongying Zan Conference proceedings 2019 Sprin

支架

Many vs. Many Query Matching with Hierarchical BERT and Transformert the transformer to accept above all matching representations, which aims to enhance the pair-wise sentence matching vector. Third, we utilize soft attention to get the importance of each matching vector for final matching prediction. Empirical studies demonstrate the effectiveness of the proposed model to query matching with informal text.

脆弱吧

A Knowledge Selective Adversarial Network for Link Prediction in Knowledge Graphances of our model KSGAN are evaluated on three standard knowledge completion datasets: FB15k-237, WN18 and WN18RR. The results show that KSGAN outperforms a list of baseline models on all the datasets, demonstrating the effectiveness of the proposed model.