scispace - formally typeset
Search or ask a question
Topic

Ranking (information retrieval)

About: Ranking (information retrieval) is a research topic. Over the lifetime, 21109 publications have been published within this topic receiving 435130 citations.


Papers
More filters
Proceedings ArticleDOI
TL;DR: LRML as mentioned in this paper proposes a new neural architecture for collaborative ranking with implicit feedback, which employs a augmented memory module and learns to attend over these memory blocks to construct latent relations, making the learned relation vector specific to each user-item pair.
Abstract: This paper proposes a new neural architecture for collaborative ranking with implicit feedback. Our model, LRML (\textit{Latent Relational Metric Learning}) is a novel metric learning approach for recommendation. More specifically, instead of simple push-pull mechanisms between user and item pairs, we propose to learn latent relations that describe each user item interaction. This helps to alleviate the potential geometric inflexibility of existing metric learing approaches. This enables not only better performance but also a greater extent of modeling capability, allowing our model to scale to a larger number of interactions. In order to do so, we employ a augmented memory module and learn to attend over these memory blocks to construct latent relations. The memory-based attention module is controlled by the user-item interaction, making the learned relation vector specific to each user-item pair. Hence, this can be interpreted as learning an exclusive and optimal relational translation for each user-item interaction. The proposed architecture demonstrates the state-of-the-art performance across multiple recommendation benchmarks. LRML outperforms other metric learning models by $6\%-7.5\%$ in terms of Hits@10 and nDCG@10 on large datasets such as Netflix and MovieLens20M. Moreover, qualitative studies also demonstrate evidence that our proposed model is able to infer and encode explicit sentiment, temporal and attribute information despite being only trained on implicit feedback. As such, this ascertains the ability of LRML to uncover hidden relational structure within implicit datasets.

98 citations

Proceedings ArticleDOI
Ziqin Wang1, Jun Xu, Li Liu, Fan Zhu, Ling Shao 
01 Oct 2019
TL;DR: In this article, a ranking attention network (RANet) is proposed to learn pixel-level similarity and segmentation in an end-to-end manner for video object segmentation.
Abstract: Despite online learning (OL) techniques have boosted the performance of semi-supervised video object segmentation (VOS) methods, the huge time costs of OL greatly restricts their practicality. Matching based and propagation based methods run at a faster speed by avoiding OL techniques. However, they are limited by sub-optimal accuracy, due to mismatching and drifting problems. In this paper, we develop a real-time yet very accurate Ranking Attention Network (RANet) for VOS. Specifically, to integrate the insights of matching based and propagation based methods, we employ an encoder-decoder framework to learn pixel-level similarity and segmentation in an end-to-end manner. To better utilize the similarity maps, we propose a novel ranking attention module, which automatically ranks and selects these maps for fine-grained VOS performance. Experiments on DAVIS16 and DAVIS17 datasets show that our RANet achieves the best speed-accuracy trade-off, e.g., with 33 milliseconds per frame and J&F=85.5% on DAVIS16. With OL, our RANet reaches J&F=87.1% on DAVIS16, exceeding state-of-the-art VOS methods. The code can be found at https://github.com/Storife/RANet.

98 citations

Patent
28 Jul 1997
TL;DR: In this paper, the display order of candidates of KANA-KANJI (Chinese character) conversion according to a noun phrase list when an inputted reading character string is converted into a KANJi-mixed character string was determined.
Abstract: PROBLEM TO BE SOLVED: To improve conversion precision by determining the display order of candidates of KANA(Japanese syllabary)-KANJI(Chinese character) conversion according to a noun phrase list when an inputted reading character string is converted into a KANJI-mixed character string. SOLUTION: When an integrated document 208 is generated by an integrated document generation module 207, a natural language process module 200 generates its noun phrase list 203. A ranking engine 204 generates a ranking list 205 wherein sentences are rearranged according to ranking by weighting respective noun phrases in the noun phrase list 203 of the inputted integrated document 208 according to the importance in the integrated document 208, deciding the importance of each noun phrase in the integrated document 208 by using the weighting results of the respective noun phrases, and ranking the noun phrases so that noun phrases of high importance are in high positions. A KANA-KANJI conversion part 209 determines conversion candidates for the reading character string and the priority according to the ranking list 205.

98 citations

Journal ArticleDOI
Răzvan V. Florian1
TL;DR: In the Shanghai ranking, the dependence between the score for the SCI indicator and the weighted number of considered articles obeys a power law, instead of the proportional dependence that is suggested by the official methodology of the ranking.
Abstract: I discuss the difficulties that I encountered in reproducing the results of the Shanghai ranking of world universities. In the Shanghai ranking, the dependence between the score for the SCI indicator and the weighted number of considered articles obeys a power law, instead of the proportional dependence that is suggested by the official methodology of the ranking. Discrepancies from proportionality are also found in some of the scores for the N&S and Size indicators. This shows that the results of the Shanghai ranking cannot be reproduced, given raw data and the public methodology of the ranking.

98 citations

Patent
19 Oct 2015
TL;DR: In this article, the authors proposed a method for communicating a ranking characterizing a portion of a roadway based on an amount of deviation between a true driving behavior on the at least one segment of the roadway and an expected driving behavior predefined for another segment.
Abstract: Methods for communicating a ranking characterizing a portion of a roadway include: (a) ranking at least one segment of a roadway based on an amount of deviation between a true driving behavior on the at least one segment of the roadway and an expected driving behavior predefined for the at least one segment of the roadway; and (b) communicating the ranking to a client. Apparatuses for communicating a ranking characterizing a portion of a roadway are described.

98 citations


Network Information
Related Topics (5)
Web page
50.3K papers, 975.1K citations
83% related
Ontology (information science)
57K papers, 869.1K citations
82% related
Graph (abstract data type)
69.9K papers, 1.2M citations
82% related
Feature learning
15.5K papers, 684.7K citations
81% related
Supervised learning
20.8K papers, 710.5K citations
81% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20241
20233,112
20226,541
20211,105
20201,082
20191,168