Community question answering (cQA) has become an important issue due to the popularity of cQA archives on the web. This paper is concerned with the problem of question retrieval. Question retrieval in cQA archives aims to find the existing questions that are semantically equivalent or relevant to the queried questions. However, the lexical gap problem brings about new challenge for question retrieval in cQA. In this paper, we propose to learn continuous word embeddings with metadata of category information within cQA pages for question retrieval. To deal with the variable size of word embedding vectors, we employ the framework of fisher kernel to aggregated them into the fixedlength vectors. Experimental results on large-scale real world cQA data set show that our approach can significantly outperform state-of-the-art translation models and topic-based models for question retrieval in cQA.
Based on observed temperature and velocity in 2005 in northwestern South China Sea, the shallow ocean responses to three tropical cyclones were examined. The oceanic response to Washi was similar to common observations with 2°C cooling of the ocean surface and slight warming of the thermocline resulted from vertical entrainment. Moreover, the wavefield was dominated by first mode near‐inertial oscillations, which were red‐shifted and trapped by negative background vorticity leading to an e‐folding timescale of 12 days. The repeated reflections by the surface and bottom boundaries were thought to yield the successive emergence of higher modes. The oceanic responses to Vicente appeared to be insignificant with cooling of the ocean surface by only 0.5°C and near‐inertial currents no larger than 0.10 m/s as a result of a deepened surface mixed layer. However, the oceanic responses to Typhoon Damrey were drastic with cooling of 4.5°C near the surface and successive barotropic‐like near‐inertial oscillations. During the forced stage, the upper ocean heat content decreased conspicuously by 11.65% and the stratification was thoroughly destroyed by vertical mixing. In the relaxation stage, the water particle had vertical displacement of 20–30 m generated by inertial pumping. The current response to Damrey was weaker than Washi due to the deepened mixed layer and the destroyed stratification. Our results suggested that the shallow water oceanic responses to tropical cyclones varied significantly with the intensity of tropical cyclones, and was affected by local stratification and background vorticity.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.