排序方式： 共有4条查询结果，搜索用时 125 毫秒
1
1.
Recent developments have shown that entity-based models that rely on information from the knowledge graph can improve document retrieval performance. However, given the non-transitive nature of relatedness between entities on the knowledge graph, the use of semantic relatedness measures can lead to topic drift. To address this issue, we propose a relevance-based model for entity selection based on pseudo-relevance feedback, which is then used to systematically expand the input query leading to improved retrieval performance. We perform our experiments on the widely used TREC Web corpora and empirically show that our proposed approach to entity selection significantly improves ad hoc document retrieval compared to strong baselines. More concretely, the contributions of this work are as follows: (1) We introduce a graphical probability model that captures dependencies between entities within the query and documents. (2) We propose an unsupervised entity selection method based on the graphical model for query entity expansion and then for ad hoc retrieval. (3) We thoroughly evaluate our method and compare it with the state-of-the-art keyword and entity based retrieval methods. We demonstrate that the proposed retrieval model shows improved performance over all the other baselines on ClueWeb09B and ClueWeb12B, two widely used Web corpora, on the [email protected], and [email protected] metrics. We also show that the proposed method is most effective on the difficult queries. In addition, We compare our proposed entity selection with a state-of-the-art entity selection technique within the context of ad hoc retrieval using a basic query expansion method and illustrate that it provides more effective retrieval for all expansion weights and different number of expansion entities. 相似文献
2.
Feras ALZOUB ZHANG Qi LI Zheng-liang 《重庆大学学报(英文版)》2007,6(4):305-310
This paper presents the results of an experimental investigation on the response of pre-damaged reinforced concrete (RC) beam strengthened in shear using applied-epoxy unidirectional carbon fiber reinforced polymer (CFRP) sheet. The reasearch included four test rectangular simply supported RC beams in shear capacity. One is the control beam, two RC beams are damaged to a predetermined degree from ultimate shear capacity of the control beam, and the last beam is left without pre-damaged and then strengthened with using externally bonded carbon fiber reinforced polymer to upgrade their shear capacity. We focused on the damage degree to beams during strengthening, therefore, only the beams with side- bonded CFRPs strips and horizontal anchored strips were used. The results show the feasibility of using CFRPs to restore or increase the load-carrying capacity in the shear of damaged RC beams. The failure mode of all the CFRP-strengthened beams is debonding of CFRP vertical strips. Two prediction available models in ACI-440 and fib European code were compared with the experimental results. 相似文献
3.
We carried out a wind tunnel test to measure cladding loads for a high-rise building of 295 m in height, which would be located in the business center of Chongqing Municipality, P. R. China. The rigid model was used to determine fluctuating local pressures on the exterior surfaces of the building. The wind tunnel test results show the cr/tical zone of wind pressures on building surfaces in both standalone and interference conditions. The computational fluid dynamics （CFD） was conducted by using the FLUENT Code to compare with the wind tunnel test results, and the steady three-dimensional turbulent flow with Realizable k-ε as a turbulence model was used. The CFD results are agree with the wind tunnel test results in regards to distributions of wind pressures over a high-rise building＇s surfaces. 相似文献
4.
Ebrahim Bagheri Faezeh Ensan Feras Al-Obeidat 《Information processing & management》2018,54(4):657-673
Learning low dimensional dense representations of the vocabularies of a corpus, known as neural embeddings, has gained much attention in the information retrieval community. While there have been several successful attempts at integrating embeddings within the ad hoc document retrieval task, yet, no systematic study has been reported that explores the various aspects of neural embeddings and how they impact retrieval performance. In this paper, we perform a methodical study on how neural embeddings influence the ad hoc document retrieval task. More specifically, we systematically explore the following research questions: (i) do methods solely based on neural embeddings perform competitively with state of the art retrieval methods with and without interpolation? (ii) are there any statistically significant difference between the performance of retrieval models when based on word embeddings compared to when knowledge graph entity embeddings are used? and (iii) is there significant difference between using locally trained neural embeddings compared to when globally trained neural embeddings are used? We examine these three research questions across both hard and all queries. Our study finds that word embeddings do not show competitive performance to any of the baselines. In contrast, entity embeddings show competitive performance to the baselines and when interpolated, outperform the best baselines for both hard and soft queries. 相似文献
1