Search

Question Generation (QG), which aims to generate a question given the relevant context, is essential to build conversational and question–answering systems. Existing neural question generation models suffer from the inadequate representation of the target answer and inappropriate techniques to reduce repetition. To address these issues, we propose an Extended Answer-aware Network (EAN) which is trained with Word-based Coverage Mechanism (WCM) and decoded with Uncertainty-aware Beam Search (UBS). The EAN represents the target answer by its surrounding sentence with an encoder and incorporates the extended answer to paragraph representation using gated paragraph-to-answer attention to tackle the problem of the inadequate representation of the target answer. To reduce undesirable repetition, the WCM penalizes repeatedly attending to the same words of different time-steps in the training stage. The UBS incorporates an uncertainty score into beam search to alleviate text degeneration and reduce repeated copying words of the paragraph. Experiments on two benchmark datasets demonstrate the effectiveness of our methods of paragraph-level question generation. Specifically, our model has achieved 4.2% and 27.2% improvement over BLEU-4 compared to the best paragraph-level QG baseline in SQuAD and NewsQA datasets respectively. [ABSTRACT FROM AUTHOR]

Cross-domain recommendation can alleviate the data sparsity problem in the target domain and has become a promising research area. Recently, various models have been proposed to provide recommendation across domains. Some models successfully embedded adversarial learning to reduce domain discrepancies between the source and target domains; however, these models only focuse on extracting the domain-shared features among multiple domains. In this paper, we devise a novel framework that considers both domain-shared and domain-specific knowledge across domains, namely, DAAN. Specifically, we tightly couple matrix factorization-based collaborative filtering with deep adversarial domain adaptation via an attention network. In this framework, we first learn the domain-specific representations for each user and each item from the source and target user-item interaction matrices. Then, we capture the domain-shared features between two domains with common user (or item) embeddings in a domain-adversarial paradigm. Additionally, an attention network is used to adjust the degree of importance between domain-shared and domain-specific knowledge. Extensive experiments on six tasks demonstrate that our method outperforms various baselines in terms of two ranking metrics. To the best of our knowledge, our proposed approach is the first deep model that considers both domain-shared and domain-specific knowledge across domains within a domain-adversarial training paradigm for cross-domain recommendation. [ABSTRACT FROM AUTHOR]

With large-scale human-annotated pixel-level annotations, many deep learning-based methods have achieved impressive innovations in the field of semantic image segmentation. However, the lack of publicly available Chinese landscape paintings with pixel-level annotations seriously hinders the process of segmentation of Chinese landscape paintings. In addition, a prominent feature of Chinese landscape paintings is the extensive use of black ink, resulting in a lack of color-related information, and landscape paintings often use blank space to depict sky and water elements, which can lead to confusion about boundary information. These issues make the semantic segmentation of Chinese landscape paintings more challenging. To address these challenges, we construct a Segmented Chinese Landscape Paintings (SegCLP) dataset, which contains 709 images with pixel-level annotations belonging to 6 foreground object classes. Moreover, we propose a novel approach called Decrease Dilation Rate Residual Attention Network (DRANet) to enable accurate semantic segmentation of Chinese landscape paintings. DRANet integrates two primary modules: an attention mechanism and a residual module. The attention module alleviates the training burden associated with the spatial convolution pool pyramid, while the residual block enhances the granularity of the decoder, particularly at the segmentation boundary. Experimental findings corroborate the superior efficacy of DRANet in accurately segmenting Chinese landscape images. [ABSTRACT FROM AUTHOR]