scispace - formally typeset
Search or ask a question

Showing papers on "Ranking (information retrieval) published in 2015"


Proceedings Article
07 Dec 2015
TL;DR: This article used the continuity of text from books to train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage, which can produce highly generic sentence representations that are robust and perform well in practice.
Abstract: We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage. Sentences that share semantic and syntactic properties are thus mapped to similar vector representations. We next introduce a simple vocabulary expansion method to encode words that were not seen as part of training, allowing us to expand our vocabulary to a million words. After training our model, we extract and evaluate our vectors with linear models on 8 tasks: semantic relatedness, paraphrase detection, image-sentence ranking, question-type classification and 4 benchmark sentiment and subjectivity datasets. The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice.

1,802 citations


Book ChapterDOI
12 Oct 2015
TL;DR: This paper proposes the triplet network model, which aims to learn useful representations by distance comparisons, and demonstrates using various datasets that this model learns a better representation than that of its immediate competitor, the Siamese network.
Abstract: Deep learning has proven itself as a successful set of models for learning useful semantic representations of data. These, however, are mostly implicitly learned as part of a classification task. In this paper we propose the triplet network model, which aims to learn useful representations by distance comparisons. A similar model was defined by Wang et al. (2014), tailor made for learning a ranking for image information retrieval. Here we demonstrate using various datasets that our model learns a better representation than that of its immediate competitor, the Siamese network. We also discuss future possible usage as a framework for unsupervised learning.

1,635 citations


Posted Content
TL;DR: The approach for unsupervised learning of a generic, distributed sentence encoder is described, using the continuity of text from books to train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage.
Abstract: We describe an approach for unsupervised learning of a generic, distributed sentence encoder. Using the continuity of text from books, we train an encoder-decoder model that tries to reconstruct the surrounding sentences of an encoded passage. Sentences that share semantic and syntactic properties are thus mapped to similar vector representations. We next introduce a simple vocabulary expansion method to encode words that were not seen as part of training, allowing us to expand our vocabulary to a million words. After training our model, we extract and evaluate our vectors with linear models on 8 tasks: semantic relatedness, paraphrase detection, image-sentence ranking, question-type classification and 4 benchmark sentiment and subjectivity datasets. The end result is an off-the-shelf encoder that can produce highly generic sentence representations that are robust and perform well in practice. We will make our encoder publicly available.

1,115 citations


Proceedings ArticleDOI
07 Jun 2015
TL;DR: A conditional random field model that reasons about possible groundings of scene graphs to test images and shows that the full model can be used to improve object localization compared to baseline methods and outperforms retrieval methods that use only objects or low-level image features.
Abstract: This paper develops a novel framework for semantic image retrieval based on the notion of a scene graph. Our scene graphs represent objects (“man”, “boat”), attributes of objects (“boat is white”) and relationships between objects (“man standing on boat”). We use these scene graphs as queries to retrieve semantically related images. To this end, we design a conditional random field model that reasons about possible groundings of scene graphs to test images. The likelihoods of these groundings are used as ranking scores for retrieval. We introduce a novel dataset of 5,000 human-generated scene graphs grounded to images and use this dataset to evaluate our method for image retrieval. In particular, we evaluate retrieval using full scene graphs and small scene subgraphs, and show that our method outperforms retrieval methods that use only objects or low-level image features. In addition, we show that our full model can be used to improve object localization compared to baseline methods.

1,006 citations


Journal ArticleDOI
TL;DR: Eight well-known similarity/distance metrics are compared on a large dataset of molecular fingerprints with sum of ranking differences (SRD) and ANOVA analysis and the Tanimoto index, Dice index, Cosine coefficient and Soergel distance were identified to be the best metrics for similarity calculations.
Abstract: Cheminformaticians are equipped with a very rich toolbox when carrying out molecular similarity calculations. A large number of molecular representations exist, and there are several methods (similarity and distance metrics) to quantify the similarity of molecular representations. In this work, eight well-known similarity/distance metrics are compared on a large dataset of molecular fingerprints with sum of ranking differences (SRD) and ANOVA analysis. The effects of molecular size, selection methods and data pretreatment methods on the outcome of the comparison are also assessed. A supplier database ( https://mcule.com/ ) was used as the source of compounds for the similarity calculations in this study. A large number of datasets, each consisting of one hundred compounds, were compiled, molecular fingerprints were generated and similarity values between a randomly chosen reference compound and the rest were calculated for each dataset. Similarity metrics were compared based on their ranking of the compounds within one experiment (one dataset) using sum of ranking differences (SRD), while the results of the entire set of experiments were summarized on box and whisker plots. Finally, the effects of various factors (data pretreatment, molecule size, selection method) were evaluated with analysis of variance (ANOVA). This study complements previous efforts to examine and rank various metrics for molecular similarity calculations. Here, however, an entirely general approach was taken to neglect any a priori knowledge on the compounds involved, as well as any bias introduced by examining only one or a few specific scenarios. The Tanimoto index, Dice index, Cosine coefficient and Soergel distance were identified to be the best (and in some sense equivalent) metrics for similarity calculations, i.e. these metrics could produce the rankings closest to the composite (average) ranking of the eight metrics. The similarity metrics derived from Euclidean and Manhattan distances are not recommended on their own, although their variability and diversity from other similarity metrics might be advantageous in certain cases (e.g. for data fusion). Conclusions are also drawn regarding the effects of molecule size, selection method and data pretreatment on the ranking behavior of the studied metrics.

770 citations


Posted Content
TL;DR: In this work, deep convolutional neural network is incorporated into hash functions to jointly learn feature representations and mappings from them to hash codes, which avoids the limitation of semantic representation power of hand-crafted features.
Abstract: With the rapid growth of web images, hashing has received increasing interests in large scale image retrieval. Research efforts have been devoted to learning compact binary codes that preserve semantic similarity based on labels. However, most of these hashing methods are designed to handle simple binary similarity. The complex multilevel semantic structure of images associated with multiple labels have not yet been well explored. Here we propose a deep semantic ranking based method for learning hash functions that preserve multilevel semantic similarity between multi-label images. In our approach, deep convolutional neural network is incorporated into hash functions to jointly learn feature representations and mappings from them to hash codes, which avoids the limitation of semantic representation power of hand-crafted features. Meanwhile, a ranking list that encodes the multilevel similarity information is employed to guide the learning of such deep hash functions. An effective scheme based on surrogate loss is used to solve the intractable optimization problem of nonsmooth and multivariate ranking measures involved in the learning procedure. Experimental results show the superiority of our proposed approach over several state-of-the-art hashing methods in term of ranking evaluation metrics when tested on multi-label image datasets.

520 citations


Proceedings ArticleDOI
01 May 2015
TL;DR: This work develops a multi-task DNN for learning representations across multiple tasks, not only leveraging large amounts of cross-task data, but also benefiting from a regularization effect that leads to more general representations to help tasks in new domains.
Abstract: Methods of deep neural networks (DNNs) have recently demonstrated superior performance on a number of natural language processing tasks. However, in most previous work, the models are learned based on either unsupervised objectives, which does not directly optimize the desired task, or singletask supervised objectives, which often suffer from insufficient training data. We develop a multi-task DNN for learning representations across multiple tasks, not only leveraging large amounts of cross-task data, but also benefiting from a regularization effect that leads to more general representations to help tasks in new domains. Our multi-task DNN approach combines tasks of multiple-domain classification (for query classification) and information retrieval (ranking for web search), and demonstrates significant gains over strong baselines in a comprehensive set of domain adaptation.

436 citations


Journal ArticleDOI
TL;DR: An up-to-date tutorial about multilabel learning is presented that introduces the paradigm and describes the main contributions developed and Evaluation measures, fields of application, trending topics, and resources are presented.
Abstract: Multilabel learning has become a relevant learning paradigm in the past years due to the increasing number of fields where it can be applied and also to the emerging number of techniques that are being developed. This article presents an up-to-date tutorial about multilabel learning that introduces the paradigm and describes the main contributions developed. Evaluation measures, fields of application, trending topics, and resources are also presented.

431 citations


Journal ArticleDOI
TL;DR: The proposed approach is based on large margin structured output learning and the visual consistency is integrated with the click features through a hypergraph regularizer term and a novel algorithm to optimize the objective function is designed.
Abstract: The inconsistency between textual features and visual contents can cause poor image search results. To solve this problem, click features, which are more reliable than textual information in justifying the relevance between a query and clicked images, are adopted in image ranking model. However, the existing ranking model cannot integrate visual features, which are efficient in refining the click-based search results. In this paper, we propose a novel ranking model based on the learning to rank framework. Visual features and click features are simultaneously utilized to obtain the ranking model. Specifically, the proposed approach is based on large margin structured output learning and the visual consistency is integrated with the click features through a hypergraph regularizer term. In accordance with the fast alternating linearization method, we design a novel algorithm to optimize the objective function. This algorithm alternately minimizes two different approximations of the original objective function by keeping one function unchanged and linearizing the other. We conduct experiments on a large-scale dataset collected from the Microsoft Bing image search engine, and the results demonstrate that the proposed learning to rank models based on visual features and user clicks outperforms state-of-the-art algorithms.

382 citations


Proceedings ArticleDOI
07 Jun 2015
TL;DR: Zhang et al. as discussed by the authors proposed a deep semantic ranking based method for learning hash functions that preserve multilevel semantic similarity between multi-label images, which avoids the limitation of semantic representation power of hand-crafted features.
Abstract: With the rapid growth of web images, hashing has received increasing interests in large scale image retrieval. Research efforts have been devoted to learning compact binary codes that preserve semantic similarity based on labels. However, most of these hashing methods are designed to handle simple binary similarity. The complex multi-level semantic structure of images associated with multiple labels have not yet been well explored. Here we propose a deep semantic ranking based method for learning hash functions that preserve multilevel semantic similarity between multi-label images. In our approach, deep convolutional neural network is incorporated into hash functions to jointly learn feature representations and mappings from them to hash codes, which avoids the limitation of semantic representation power of hand-crafted features. Meanwhile, a ranking list that encodes the multilevel similarity information is employed to guide the learning of such deep hash functions. An effective scheme based on surrogate loss is used to solve the intractable optimization problem of nonsmooth and multivariate ranking measures involved in the learning procedure. Experimental results show the superiority of our proposed approach over several state-of-the-art hashing methods in term of ranking evaluation metrics when tested on multi-label image datasets.

377 citations


Proceedings Article
25 Jul 2015
TL;DR: This paper proposes a personalized ranking metric embedding method (PRME) to model personalized check-in sequences and develops a PRME-G model, which integrates sequential information, individual preference, and geographical influence, to improve the recommendation performance.
Abstract: The rapidly growing of Location-based Social Networks (LBSNs) provides a vast amount of check-in data, which enables many services, e.g., point-of-interest (POI) recommendation. In this paper, we study the next new POI recommendation problem in which new POIs with respect to users' current location are to be recommended. The challenge lies in the difficulty in precisely learning users' sequential information and personalizing the recommendation model. To this end, we resort to the Metric Embedding method for the recommendation, which avoids drawbacks of the Matrix Factorization technique. We propose a personalized ranking metric embedding method (PRME) to model personalized check-in sequences. We further develop a PRME-G model, which integrates sequential information, individual preference, and geographical influence, to improve the recommendation performance. Experiments on two real-world LBSN datasets demonstrate that our new algorithm outperforms the state-of-the-art next POI recommendation methods.

Posted Content
TL;DR: NetVLAD as discussed by the authors is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval, which is readily pluggable into any CNN architecture and amenable to training via backpropagation.
Abstract: We tackle the problem of large scale visual place recognition, where the task is to quickly and accurately recognize the location of a given query photograph. We present the following three principal contributions. First, we develop a convolutional neural network (CNN) architecture that is trainable in an end-to-end manner directly for the place recognition task. The main component of this architecture, NetVLAD, is a new generalized VLAD layer, inspired by the "Vector of Locally Aggregated Descriptors" image representation commonly used in image retrieval. The layer is readily pluggable into any CNN architecture and amenable to training via backpropagation. Second, we develop a training procedure, based on a new weakly supervised ranking loss, to learn parameters of the architecture in an end-to-end manner from images depicting the same places over time downloaded from Google Street View Time Machine. Finally, we show that the proposed architecture significantly outperforms non-learnt image representations and off-the-shelf CNN descriptors on two challenging place recognition benchmarks, and improves over current state-of-the-art compact image representations on standard image retrieval benchmarks.

Journal ArticleDOI
TL;DR: A mathematical framework is described that allows us to calculate centrality in multilayer networks and rank nodes accordingly, finding the ones that play the most central roles in the cohesion of the whole structure, bridging together different types of relations.
Abstract: A challenging problem is to identify the most central agents in interconnected multilayer networks. Here, De Domenico et al. present a mathematical framework to calculate centrality in such networks—versatility—and rank nodes accordingly.

Proceedings ArticleDOI
07 Dec 2015
TL;DR: Zhang et al. as mentioned in this paper proposed a dual attribute-aware ranking network (DARN) for cross-domain image retrieval, which consists of two sub-networks, one for each domain, whose retrieval feature representations are driven by semantic attribute learning.
Abstract: We address the problem of cross-domain image retrieval, considering the following practical application: given a user photo depicting a clothing image, our goal is to retrieve the same or attribute-similar clothing items from online shopping stores. This is a challenging problem due to the large discrepancy between online shopping images, usually taken in ideal lighting/pose/background conditions, and user photos captured in uncontrolled conditions. To address this problem, we propose a Dual Attribute-aware Ranking Network (DARN) for retrieval feature learning. More specifically, DARN consists of two sub-networks, one for each domain, whose retrieval feature representations are driven by semantic attribute learning. We show that this attribute-guided learning is a key factor for retrieval accuracy improvement. In addition, to further align with the nature of the retrieval problem, we impose a triplet visual similarity constraint for learning to rank across the two subnetworks. Another contribution of our work is a large-scale dataset which makes the network learning feasible. We exploit customer review websites to crawl a large set of online shopping images and corresponding offline user photos with fine-grained clothing attributes, i.e., around 450,000 online shopping images and about 90,000 exact offline counterpart images of those online ones. All these images are collected from real-world consumer websites reflecting the diversity of the data modality, which makes this dataset unique and rare in the academic community. We extensively evaluate the retrieval performance of networks in different configurations. The top-20 retrieval accuracy is doubled when using the proposed DARN other than the current popular solution using pre-trained CNN features only (0.570 vs. 0.268).

Book
30 Jun 2015
TL;DR: This survey summarizes advances in modeling user click behavior on a web search engine result page and presents simple click models as well as more complex models aimed at improving search result ranking.
Abstract: With the rapid growth of web search in recent years the problem of modeling its users has started to attract more and more attention of the information retrieval community. This has several motivations. By building a model of user behavior we are essentially developing a better understanding of a user, which ultimately helps us to deliver a better search experience. A model of user behavior can also be used as a predictive device for non-observed items such as document relevance, which makes it useful for improving search result ranking. Finally, in many situations experimenting with real users is just infeasible and hence user simulations based on accurate models play an essential role in understanding the implications of algorithmic changes to search engine results or presentation changes to the search engine result page. In this survey we summarize advances in modeling user click behavior on a web search engine result page. We present simple click models as well as more complex models aimed at capturing non-trivial user behavior patterns on modern search engine result pages. We discuss how these models compare to each other, what challenges they have, and what ways there are to address these challenges. We also study the problem of evaluating click models and discuss the main applications of click models.

Posted Content
TL;DR: This work proposes a Dual Attribute-aware Ranking Network (DARN) for retrieval feature learning, consisting of two sub-networks, one for each domain, whose retrieval feature representations are driven by semantic attribute learning.
Abstract: We address the problem of cross-domain image retrieval, considering the following practical application: given a user photo depicting a clothing image, our goal is to retrieve the same or attribute-similar clothing items from online shopping stores. This is a challenging problem due to the large discrepancy between online shopping images, usually taken in ideal lighting/pose/background conditions, and user photos captured in uncontrolled conditions. To address this problem, we propose a Dual Attribute-aware Ranking Network (DARN) for retrieval feature learning. More specifically, DARN consists of two sub-networks, one for each domain, whose retrieval feature representations are driven by semantic attribute learning. We show that this attribute-guided learning is a key factor for retrieval accuracy improvement. In addition, to further align with the nature of the retrieval problem, we impose a triplet visual similarity constraint for learning to rank across the two sub-networks. Another contribution of our work is a large-scale dataset which makes the network learning feasible. We exploit customer review websites to crawl a large set of online shopping images and corresponding offline user photos with fine-grained clothing attributes, i.e., around 450,000 online shopping images and about 90,000 exact offline counterpart images of those online ones. All these images are collected from real-world consumer websites reflecting the diversity of the data modality, which makes this dataset unique and rare in the academic community. We extensively evaluate the retrieval performance of networks in different configurations. The top-20 retrieval accuracy is doubled when using the proposed DARN other than the current popular solution using pre-trained CNN features only (0.570 vs. 0.268).

Proceedings ArticleDOI
02 Feb 2015
TL;DR: This paper proposes a probabilistic model that leverages user-generated information on the web to link queries to entities in a knowledge base and significantly outperforms several state-of-the-art baselines while being able to process queries in sub-millisecond times---at least two orders of magnitude faster than existing systems.
Abstract: Entity linking deals with identifying entities from a knowledge base in a given piece of text and has become a fundamental building block for web search engines, enabling numerous downstream improvements from better document ranking to enhanced search results pages. A key problem in the context of web search queries is that this process needs to run under severe time constraints as it has to be performed before any actual retrieval takes place, typically within milliseconds.In this paper we propose a probabilistic model that leverages user-generated information on the web to link queries to entities in a knowledge base. There are three key ingredients that make the algorithm fast and space-efficient. First, the linking process ignores any dependencies between the different entity candidates, which allows for a O(k2) implementation in the number of query terms. Second, we leverage hashing and compression techniques to reduce the memory footprint. Finally, to equip the algorithm with contextual knowledge without sacrificing speed, we factor the distance between distributional semantics of the query words and entities into the model.We show that our solution significantly outperforms several state-of-the-art baselines by more than 14% while being able to process queries in sub-millisecond times---at least two orders of magnitude faster than existing systems.

Proceedings ArticleDOI
07 Dec 2015
TL;DR: DeepBox as mentioned in this paper uses convolutional neural networks (CNNs) to rerank proposals from a bottom-up method, which leads to a 4.5-point gain in detection mAP.
Abstract: Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that "objectness" is in fact a high level construct. We argue for a data-driven, semantic approach for ranking object proposals. Our framework, which we call DeepBox, uses convolutional neural networks (CNNs) to rerank proposals from a bottom-up method. We use a novel four-layer CNN architecture that is as good as much larger networks on the task of evaluating objectness while being much faster. We show that DeepBox significantly improves over the bottom-up ranking, achieving the same recall with 500 proposals as achieved by bottom-up methods with 2000. This improvement generalizes to categories the CNN has never seen before and leads to a 4.5-point gain in detection mAP. Our implementation achieves this performance while running at 260 ms per image.

Proceedings ArticleDOI
01 Jul 2015
TL;DR: A simple, non-linear mention-ranking model for coreference resolution that attempts to learn distinct feature representations for anaphoricity detection and antecedent ranking, which is encouraged by pre-training on a pair of corresponding subtasks.
Abstract: We introduce a simple, non-linear mention-ranking model for coreference resolution that attempts to learn distinct feature representations for anaphoricity detection and antecedent ranking, which we encourage by pre-training on a pair of corresponding subtasks. Although we use only simple, unconjoined features, the model is able to learn useful representations, and we report the best overall score on the CoNLL 2012 English test set to date.

Proceedings ArticleDOI
14 Jan 2015
TL;DR: A framework to prove almost sure termination for probabilistic programs with real valued variables, based on ranking supermartingales, which is proven sound and complete for a meaningful class of programs involving randomization and bounded nondeterminism.
Abstract: We propose a framework to prove almost sure termination for probabilistic programs with real valued variables. It is based on ranking supermartingales, a notion analogous to ranking functions on non-probabilistic programs. The framework is proven sound and complete for a meaningful class of programs involving randomization and bounded nondeterminism. We complement this foundational insigh by a practical proof methodology, based on sound conditions that enable compositional reasoning and are amenable to a direct implementation using modern theorem provers. This is integrated in a small dependent type system, to overcome the problem that lexicographic ranking functions fail when combined with randomization. Among others, this compositional methodology enables the verification of probabilistic programs outside the complete class that admits ranking supermartingales.

Patent
25 Sep 2015
TL;DR: In this article, a system was proposed to highlight search terms in documents distributed over a network by generating a search query that includes a search term and receiving a list of one or more references to documents in the network.
Abstract: A system highlights search terms in documents distributed over a network. The system generates a search query that includes a search term and, in response to the search query, receives a list of one or more references to documents in the network. The system receives selection of one of the references and retrieves a document that corresponds to the selected reference. The system then highlights the search term in the retrieved document.

Journal ArticleDOI
TL;DR: A new approach based on the principle of combinatorial optimization with ranking-entropy and the least squares for determining attribute weight is given and a decision making procedure based on combined ranking value is given to select the best alternative(s).

Posted Content
TL;DR: An in-house implementation of previously reported models are used to do an independent evaluation and an ensemble is created by averaging predictions of multiple models to achieve a state-of-the-art result for the next utterance ranking on the Ubuntu Dialog Corpus.
Abstract: This paper presents results of our experiments for the next utterance ranking on the Ubuntu Dialog Corpus -- the largest publicly available multi-turn dialog corpus. First, we use an in-house implementation of previously reported models to do an independent evaluation using the same data. Second, we evaluate the performances of various LSTMs, Bi-LSTMs and CNNs on the dataset. Third, we create an ensemble by averaging predictions of multiple models. The ensemble further improves the performance and it achieves a state-of-the-art result for the next utterance ranking on this dataset. Finally, we discuss our future plans using this corpus.

Proceedings ArticleDOI
16 May 2015
TL;DR: MUSE (Method USage Examples), an approach for mining and ranking actual code examples that show how to use a specific method, combines static slicing with clone detection, and uses heuristics to select and rank the best examples in terms of reusability, understandability, and popularity.
Abstract: Code examples are small source code fragments whose purpose is to illustrate how a programming language construct, an API, or a specific function/method works. Since code examples are not always available in the software documentation, researchers have proposed techniques to automatically extract them from existing software or to mine them from developer discussions. In this paper we propose muse (Method USage Examples), an approach for mining and ranking actual code examples that show how to use a specific method. muse combines static slicing (to simplify examples) with clone detection (to group similar examples), and uses heuristics to select and rank the best examples in terms of reusability, understandability, and popularity. muse has been empirically evaluated using examples mined from six libraries, by performing three studies involving a total of 140 developers to: (i) evaluate the selection and ranking heuristics, (ii) provide their perception on the usefulness of the selected examples, and (iii) perform specific programming tasks using the muse examples. The results indicate that muse selects and ranks examples close to how humans do, most of the code examples (82%) are perceived as useful, and they actually help when performing programming tasks.

Proceedings ArticleDOI
09 Aug 2015
TL;DR: This work proposes rewriting method based on a novel query embedding algorithm, which jointly models query content as well as its context within a search session, and shows the proposed approach significantly outperformed existing state-of-the-art, strongly indicating its benefits and the monetization potential.
Abstract: Search engines represent one of the most popular web services, visited by more than 85% of internet users on a daily basis. Advertisers are interested in making use of this vast business potential, as very clear intent signal communicated through the issued query allows effective targeting of users. This idea is embodied in a sponsored search model, where each advertiser maintains a list of keywords they deem indicative of increased user response rate with regards to their business. According to this targeting model, when a query is issued all advertisers with a matching keyword are entered into an auction according to the amount they bid for the query, and the winner gets to show their ad. One of the main challenges is the fact that a query may not match many keywords, resulting in lower auction value, lower ad quality, and lost revenue for advertisers and publishers. Possible solution is to expand a query into a set of related queries and use them to increase the number of matched ads, called query rewriting. To this end, we propose rewriting method based on a novel query embedding algorithm, which jointly models query content as well as its context within a search session. As a result, queries with similar content and context are mapped into vectors close in the embedding space, which allows expansion of a query via simple K-nearest neighbor search in the projected space. The method was trained on more than 12 billion sessions, one of the largest corpuses reported thus far, and evaluated on both public TREC data set and in-house sponsored search data set. The results show the proposed approach significantly outperformed existing state-of-the-art, strongly indicating its benefits and the monetization potential.

Journal ArticleDOI
TL;DR: A novel category-aware service clustering and distributed recommending method is proposed for automatic mashup creation and Experiments on a real-world dataset have proved that the proposed approach not only gains significant improvement at precision rate but also enhances the diversity of recommendation results.
Abstract: Mashup has emeraged as a promising way to allow developers to compose existed APIs (services) to create new or value-added services. With the rapid increasing number of services published on the Internet, service recommendation for automatic mashup creation gains a lot of momentum. Since mashup inherently requires services with different functions, the recommendation result should contain services from various categories. However, most existing recommendation approaches only rank all candidate services in a single list, which has two deficiencies. First, ranking services without considering to which categories they belong may lead to meaningless service ranking and affect the recommendation accuracy. Second, mashup developers are not always clear about which service categories they need and services in which categories cooperate better for mashup creation. Without explicitly recommending which service categories are relevant for mashup creation, it remains difficult for mashup developers to select proper services in a mixed ranking list, which lower the user friendliness of recommendation. To overcome these deficiencies, a novel category-aware service clustering and distributed recommending method is proposed for automatic mashup creation. First, a Kmeans variant ( vKmeans ) method based on topic model Latent Dirichlet Allocation is introduced for enhancing service categorization and providing a basis for recommendation. Second, on top of vKmeans , a service category relevance ranking ( SCRR ) model, which combines machine learning and collaborative filtering, is developed to decompose mashup requirements and explicitly predict relevant service categories. Finally, a category-aware distributed service recommendation ( CDSR ) model, which is based on a distributed machine learning framework, is developed for predicting service ranking order within each category. Experiments on a real-world dataset have proved that the proposed approach not only gains significant improvement at precision rate but also enhances the diversity of recommendation results.

Book
27 Feb 2015
TL;DR: A formal definition of the search result diversification problem is provided and the most successful approaches in the literature for producing and evaluating diversity in multiple search domains are described.
Abstract: Ranking in information retrieval has been traditionally approachedas a pursuit of relevant information, under the assumption that theusers' information needs are unambiguously conveyed by their submittedqueries. Nevertheless, as an inherently limited representation of amore complex information need, every query can arguably be consideredambiguous to some extent. In order to tackle query ambiguity,search result diversification approaches have recently been proposed toproduce rankings aimed to satisfy the multiple possible informationneeds underlying a query. In this survey, we review the published literatureon search result diversification. In particular, we discuss themotivations for diversifying the search results for an ambiguous queryand provide a formal definition of the search result diversification problem.In addition, we describe the most successful approaches in theliterature for producing and evaluating diversity in multiple search domains.Finally, we also discuss recent advances as well as open researchdirections in the field of search result diversification.

Journal ArticleDOI
TL;DR: Thorough experiments suggest that the proposed saliency- inspired fast image retrieval scheme, S-sim, significantly speeds up online retrieval and outperforms the state-of-the-art BoW-based image retrieval schemes.
Abstract: The bag-of-visual-words (BoW) model is effective for representing images and videos in many computer vision problems, and achieves promising performance in image retrieval. Nevertheless, the level of retrieval efficiency in a large-scale database is not acceptable for practical usage. Considering that the relevant images in the database of a given query are more likely to be distinctive than ambiguous, this paper defines “database saliency” as the distinctiveness score calculated for every image to measure its overall “saliency” in the database. By taking advantage of database saliency, we propose a saliency- inspired fast image retrieval scheme, S-sim, which significantly improves efficiency while retains state-of-the-art accuracy in image retrieval . There are two stages in S-sim: the bottom-up saliency mechanism computes the database saliency value of each image by hierarchically decomposing a posterior probability into local patches and visual words, the concurrent information of visual words is then bottom-up propagated to estimate the distinctiveness, and the top-down saliency mechanism discriminatively expands the query via a very low-dimensional linear SVM trained on the top-ranked images after initial search, ranking images are then sorted on their distances to the decision boundary as well as the database saliency values. We comprehensively evaluate S-sim on common retrieval benchmarks, e.g., Oxford and Paris datasets. Thorough experiments suggest that, because of the offline database saliency computation and online low-dimensional SVM, our approach significantly speeds up online retrieval and outperforms the state-of-the-art BoW-based image retrieval schemes.

01 Jun 2015
TL;DR: The authors proposed a novel approach where the output layer of a character-level RNN language model is split into several independent predictive sub-models, each representing an author, while the recurrent layer is shared by all.
Abstract: Recurrent neural networks (RNNs) are very good at modelling the flow of text, but typically need to be trained on a far larger corpus than is available for the PAN 2015 Author Identification task. This paper describes a novel approach where the output layer of a character-level RNN language model is split into several independent predictive sub-models, each representing an author, while the recurrent layer is shared by all. This allows the recurrent layer to model the language as a whole without over-fitting, while the outputs select aspects of the underlying model that reflect their author's style. The method proves competitive, ranking first in two of the four languages.

Proceedings ArticleDOI
07 Dec 2015
TL;DR: This paper introduces an unsupervised ranking optimization approach based on discriminant context information analysis that refines a given initial ranking by removing the visual ambiguities common to first ranks.
Abstract: Person re-identification is an open and challenging problem in computer vision. Existing re-identification approaches focus on optimal methods for features matching (e.g., metric learning approaches) or study the inter-camera transformations of such features. These methods hardly ever pay attention to the problem of visual ambiguities shared between the first ranks. In this paper, we focus on such a problem and introduce an unsupervised ranking optimization approach based on discriminant context information analysis. The proposed approach refines a given initial ranking by removing the visual ambiguities common to first ranks. This is achieved by analyzing their content and context information. Extensive experiments on three publicly available benchmark datasets and different baseline methods have been conducted. Results demonstrate a remarkable improvement in the first positions of the ranking. Regardless of the selected dataset, state-of-the-art methods are strongly outperformed by our method.