This paper describes our system for SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge (Ostermann et al., 2018b).We use Threeway Attentive Networks (TriAN) to model interactions between the passage, question and answers. To incorporate commonsense knowledge, we augment the input with relation embedding from the graph of general knowledge ConceptNet (Speer et al., 2017). As a result, our system achieves state-of-the-art performance with 83.95% accuracy on the official test data. Code is publicly available at https://github.com/ intfloat/commonsense-rc.

Residents of a particular destination are potentially the largest and most powerful stakeholders of destination brands. However, the basis of residents' attitudes toward destination branding is not widely understood. In this study, it is proposed that selfcongruity (the degree of match between the perceived self and perceived brand identity) is a possible antecedent of these attitudes. We empirically demonstrate that brand self-congruity is a likely indicator of destination brand attitude and that subsequent ambassadorial behavior among residents is probable. Implications for practitioners and future research opportunities are finally suggested.

In this paper, we propose a weakly supervised temporal action localization method on untrimmed videos based on prototypical networks. We observe two challenges posed by weakly supervision, namely action-background separation and action relation construction. Unlike the previous method, we propose to achieve action-background separation only by the original videos. To achieve this, a clustering loss is adopted to separate actions from backgrounds and learn intra-compact features, which helps in detecting complete action instances. Besides, a similarity weighting module is devised to further separate actions from backgrounds. To effectively identify actions, we propose to construct relations among actions for prototype learning. A GCN-based prototype embedding module is introduced to generate relational prototypes. Experiments on THUMOS14 and ActivityNet1.2 datasets show that our method outperforms the state-of-the-art methods.

No abstract

No abstract