Social annotation in query expansion

Lin, Yuan; Lin, Hongfei; Jin, Song; Zheng, Yi

doi:10.1145/2009916.2009972

Cited by 38 publications

(50 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We set the default parameter values k 1 = 1.2, k 3 = 8 and b = 0.75, as baseline for our evaluation. As a query expansion model, we use the basic KL divergence model (KL) and the machine learning (ML) approach with the baseline features as proposed Lin et al [89] as baseline (KLML). For simplicity and readability, we only show the results of KL since we observed that the MAP values of KLML are comparable with MAP values of KL.…”

Section: Baseline Methodsmentioning

confidence: 99%

“…Such feature vectors are composed by traditional statistical features based on the distribution of the terms both in the whole collection, and the set of (pseudo) relevant documents. Lin et al [89] propose an extension of this work by applying a learning to rank approach for training and classifying the candidate expansion terms. They show that they can improve the retrieval effectiveness by using social annotation from external tagged resources, such as the de.li.cio.us 2 social bookmarking Web service, as a source for extracting useful expansion terms.…”

Section: Relation To Other Workmentioning

confidence: 99%

“…They were chosen based on the assumption that terms that contribute to improve the retrieval effectiveness are those that are most frequent and distinctive [24]. As proposed by Cao et al [24] and Lin et al [89], we can use features related to the distribution of the candidate term e in feedback documents and the whole collection, and those capturing the co-occurrence of e with the terms in the original query q. In our experiments, they constitute the features in the baseline approach, which basically consist of traditional statistical features such as Document Frequency (DF).…”

Section: Feature Setmentioning

confidence: 99%

See 2 more Smart Citations

Geo-Temporal Mining and Searching of Events from Web-based Image Collections

Ruocco

2014

SIGIR Forum

View full text Add to dashboard Cite

The proliferation of Web-and social media-based photo-sharing applications have not only opened many possibilities but also resulted in new needs and challenges. They have resulted in a large amount of personal photos being available for public access. One of the most interesting characteristics of these data is that they are surrounded by 1) textual annotations, also called tags, which are intended to describe and categorize, by collective user efforts, the uploaded resources 2) temporal information referring to when a pictures has been taken and often by 3) a locational information describing where the picture has been taken. Despite the recent developments and technological advances in Web-based media-sharing applications, the continuously increasing amount of available information has made the access to the photos a demanding task. In general, we can address this challenge by allowing photo collections to be organized and browsed through the concept of events. We also believe most users are familiar with searching photo collections using events as starting points.Aiming at supporting the detection and search of event-related photos, this thesis proposes a novel framework for extracting pictures related to real-life events from a collection of Web-images by leveraging on their temporal geographical and textual annotations and comparing the proposed approach with existing related state-ofthe-art approaches. Second, a set of geographical features is proposed describing the characteristics of the geographical profile of query terms deriving concepts from exploratory analysis. Third, the thesis provides two different tag-based search framework to improve the effectiveness of searching images related to events. The first framework is based on temporal and geographical proximity of query terms to the temporal neighbors of a given timestamped query, while the second framework is based on a novel machine-learning based query expansion method combining the heterogeneous textual, temporal and geographical similarity between query terms and candidate expansion terms for the selection of the expansion terms given a free text textual query.All the proposed methods have been evaluated by performing extensive experiments on real data gathered from media-sharing applications on the Web. Where possible, comparison with related techniques has been performed to reinforce the validity of the presented approaches. The proposed methods have shown promising results in both the extraction and clustering of event-related images and searching eventrelated pictures by using metrics from the state of the art.i ii Preface

show abstract

Section: Baseline Methodsmentioning

confidence: 99%

Section: Relation To Other Workmentioning

confidence: 99%

Section: Feature Setmentioning

confidence: 99%

See 1 more Smart Citation

Geo-Temporal Mining and Searching of Events from Web-based Image Collections

Ruocco

2014

SIGIR Forum

View full text Add to dashboard Cite

show abstract

“…Yin et al [13] utilized the hints such as query logs, snippets and search result documents from external search engines to expand the initial query. Lin et al [14] extracted candidate expansion terms by a term-dependency method and ranked them based on social annotation resource. Oliveira et al [15] proposed to expand entityrelated queries using wikipedia articles and tag recommendation methods.…”

Section: Related Workmentioning

confidence: 99%

“…Re-retrieval of new pages based on query expansion or reformulation is another effective strategy for improving retrieval accuracy, when initial search results in response to a query contain no pages relevant to users' search intentions. Query expansion or reformulation involves expanding or revising the search query to match additional or new pages by utilizing some technologies and information such as global analysis [9], pseudo-relevance feedback [10], users' personal information repository [11], term classification [12], hints obtained from external Web search engines [13], social annotation [14], wikipedia articles [15], and automatic diagnosis of term mismatch [16].…”

Section: Introductionmentioning

confidence: 99%

Personalized Web Search Using Emotional Features

Zhang

Minami

Kawai

et al. 2013

Availability, Reliability, and Security in Information Systems and HCI

View full text Add to dashboard Cite

Learning to expand queries using entities

Brandão

Santos

Ziviani

et al. 2014

Asso for Info Science & Tech

View full text Add to dashboard Cite

A substantial fraction of web search queries contain references to entities, such as persons, organizations, and locations. Recently, methods that exploit named entities have been shown to be more effective for query expansion than traditional pseudorelevance feedback methods. In this article, we introduce a supervised learning approach that exploits named entities for query expansion using Wikipedia as a repository of high‐quality feedback documents. In contrast with existing entity‐oriented pseudorelevance feedback approaches, we tackle query expansion as a learning‐to‐rank problem. As a result, not only do we select effective expansion terms but we also weigh these terms according to their predicted effectiveness. To this end, we exploit the rich structure of Wikipedia articles to devise discriminative term features, including each candidate term's proximity to the original query terms, as well as its frequency across multiple article fields and in category and infobox descriptors. Experiments on three Text REtrieval Conference web test collections attest the effectiveness of our approach, with gains of up to 23.32% in terms of mean average precision, 19.49% in terms of precision at 10, and 7.86% in terms of normalized discounted cumulative gain compared with a state‐of‐the‐art approach for entity‐oriented query expansion.

show abstract

Social annotation in query expansion

Cited by 38 publications

References 25 publications

Geo-Temporal Mining and Searching of Events from Web-based Image Collections

Geo-Temporal Mining and Searching of Events from Web-based Image Collections

Personalized Web Search Using Emotional Features

Learning to expand queries using entities

Contact Info

Product

Resources

About