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.

Discovering informative connection subgraphs in multi-relational graphs

Abstract: Discovering patterns in graphs has long been an area of interest. In most approaches to such pattern discovery either quantitative anomalies, frequency of substructure or maximum flow is used to measure the interestingness of a pattern. In this paper we introduce heuristics that guide a subgraph discovery algorithm away from banal paths towards more "informative" ones. Given an RDF graph a user might pose a question of the form: "What are the most relevant ways in which entity X is related to entity Y?" the response to which is a subgraph connecting X to Y. We use our heuristics to discover informative subgraphs within RDF graphs. Our heuristics are based on weighting mechanisms derived from edge semantics suggested by the RDF schema. We present an analysis of the quality of the subgraphs generated with respect to path ranking metrics. We then conclude presenting intuitions about which of our weighting schemes and heuristics produce higher quality subgraphs.

Information Retrieval: Searching in the 21st Century

Abstract: Foreword. Preface. About the Editors. List of Contributors. Introduction. 1 Information Retrieval Models ( Djoerd Hiemstra). 1.1 Introduction. 1.2 Exact Match Models. 1.3 Vector Space Approaches. 1.4 Probabilistic Approaches. 1.5 Summary and Further Reading. Exercises. References. 2 User-centred Evaluation of Information Retrieval Systems ( Pia Borlund). 2.1 Introduction. 2.2 The MEDLARS Test. 2.3 The Okapi Project. 2.4 The Interactive IR Evaluation Model. 2.5 Summary. Exercises. References. 3 Multimedia Resource Discovery ( Stefan R u ger). 3.1 Introduction. 3.2 Basic Multimedia Search Technologies. 3.3 Challenges of Automated Visual Indexing. 3.4 Added Services. 3.5 Browsing: Lateral and Geotemporal. 3.6 Summary. Exercises. References. 4 Image Users' Needs and Searching Behaviour ( Stina Westman). 4.1 Introduction. 4.2 Image Attributes and Users' Needs. 4.3 Image Searching Behaviour. 4.4 New Directions for Image Access. 4.5 Summary. Exercises. References. 5 Web Information Retrieval ( Nick Craswell and David Hawking). 5.1 Introduction. 5.2 Distinctive Characteristics of the Web. 5.3 Three Ranking Problems. 5.4 Other Web IR Issues. 5.5 Evaluation of Web Search Effectiveness. 5.6 Summary. Exercises. References. 6 Mobile Search ( David Mountain, Hans Myrhaug and Ay s e G o ker). 6.1 Introduction: Mobile Search - Why Now? 6.2 Information for Mobile Search. 6.3 Designing for Mobile Search. 6.4 Case Studies. 6.5 Summary. Exercises. References. 7 Context and Information Retrieval ( Ay s e G o ker, Hans Myrhaug and Ralf Bier). 7.1 Introduction. 7.2 What is Context? 7.3 Context in Information Retrieval. 7.4 Context Modelling and Representation. 7.5 Context and Content. 7.6 Related Topics. 7.7 Evaluating Context-aware IR Systems. 7.8 Summary. Exercises. References. 8 Text Categorisation and Genre in Information Retrieval ( Stuart Watt). 8.1 Introduction: What is Text Categorisation? 8.2 How to Build a Text Categorisation System. 8.3 Evaluating Text Categorisation Systems. 8.4 Genre: Text Structure and Purpose. 8.5 Related Techniques: Information Filtering. 8.6 Applications of Text Categorisation. 8.7 Summary and the Future of Text Categorisation. Exercises. References. 9 Semantic Search ( John Davies, Alistair Duke and Atanas Kiryakov). 9.1 Introduction. 9.2 Semantic Web. 9.3 Metadata and Annotations. 9.4 Semantic Annotations: the Fibres of the Semantic Web. 9.5 Semantic Annotation of Named Entities. 9.6 Semantic Indexing and Retrieval. 9.7 Semantic Search Tools. 9.8 Summary. Exercises. References. 10 The Role of Natural Language Processing in Information Retrieval: Searching for Meaning and Structure ( Tony Russell-Rose and Mark Stevenson). 10.1 Introduction. 10.2 Natural Language Processing Techniques. 10.3 Applications of Natural Language Processing in Information Retrieval. 10.4 Discussion. 10.5 Summary. Exercises. References. 11 Cross-Language Information Retrieval ( Daqing He and Jianqiang Wang). 11.1 Introduction. 11.2 Major Approaches and Challenges in CLIR. 11.3 Identifying Translation Units. 11.4 Obtaining Translation Knowledge. 11.5 Using Translation Knowledge. 11.6 Interactivity in CLIR. 11.7 Evaluation of CLIR Systems. 11.8 Summary and Future Directions. Exercises. References. 12 Performance Issues in Parallel Computing for Information Retrieval (Andrew MacFarlane). 12.1 Introduction. 12.2 Why Parallel IR? 12.3 Review of Previous Work. 12.4 Distribution Methods for Inverted File Data. 12.5 Tasks in Information Retrieval. 12.6 A Synthetic Model of Performance for Parallel Information Retrieval. 12.7 Empirical Examination of Synthetic Model. 12.8 Summary and Further Research. Exercises. References. Solutions to Exercises. Index.

Modeling Stylized Character Expressions via Deep Learning

Abstract: We propose DeepExpr, a novel expression transfer approach from humans to multiple stylized characters. We first train two Convolutional Neural Networks to recognize the expression of humans and stylized characters independently. Then we utilize a transfer learning technique to learn the mapping from humans to characters to create a shared embedding feature space. This embedding also allows human expression-based image retrieval and character expression-based image retrieval. We use our perceptual model to retrieve character expressions corresponding to humans. We evaluate our method on a set of retrieval tasks on our collected stylized character dataset of expressions. We also show that the ranking order predicted by the proposed features is highly correlated with the ranking order provided by a facial expression expert and Mechanical Turk experiments.

Neural Personalized Ranking for Image Recommendation

Abstract: We propose a new model toward improving the quality of image recommendations in social sharing communities like Pinterest, Flickr, and Instagram. Concretely, we propose Neural Personalized Ranking (NPR) -- a personalized pairwise ranking model over implicit feedback datasets -- that is inspired by Bayesian Personalized Ranking (BPR) and recent advances in neural networks. We further build an enhanced model by augmenting the basic NPR model with multiple contextual preference clues including user tags, geographic features, and visual factors. In our experiments over the Flickr YFCC100M dataset, we demonstrate the proposed NPR model is more effective than multiple baselines. Moreover, the contextual enhanced NPR model significantly outperforms the base model by 16.6% and a contextual enhanced BPR model by 4.5% in precision and recall.

Terms of a feather: content-based news recommendation and discovery using twitter

Abstract: User-generated content has dominated the web's recent growth and today the so-called real-time web provides us with unprecedented access to the real-time opinions, views, and ratings of millions of users. For example, Twitter's 200m+ users are generating in the region of 1000+ tweets per second. In this work, we propose that this data can be harnessed as a useful source of recommendation knowledge. We describe a social news service called Buzzer that is capable of adapting to the conversations that are taking place on Twitter to ranking personal RSS subscriptions. This is achieved by a content-based approach of mining trending terms from both the public Twitter timeline and from the timeline of tweets published by a user's own Twitter friend subscriptions. We also present results of a live-user evaluation which demonstrates how these ranking strategies can add better item filtering and discovery value to conventional recency-based RSS ranking techniques.