Filters








16,244 Hits in 4.7 sec

Employing open-web for Contextual Suggestion using tag-tag similarity

Sainyam Kapoor, Manajit Chakraborty, C. Ravindranath Chowdary
2016 Text Retrieval Conference  
We employ open-web information in a novel way to capture the best possible setting for a user's tastes and distastes in terms of tag scores.  ...  The TREC 2016 Contextual Suggestion task aims at providing recommendations on points of attraction for different kind of users and a varying context.  ...  All the three techniques employed open-web information in the form of Wikipedia pages associated with the tags and designed heuristics to calculate the score of each candidate suggestion accordingly.  ... 
dblp:conf/trec/KapoorCC16 fatcat:fyt4selpdjhb7k26yhpeiclcbm

Overview of the TREC 2016 Contextual Suggestion Track

Seyyed Hadi Hashemi, Jaap Kamps, Julia Kiseleva, Charles L. A. Clarke, Ellen M. Voorhees
2016 Text Retrieval Conference  
First, the TREC CS web corpus, consisting of a web crawl of the TREC contextual suggestion collection, was made available.  ...  Previously, reusability of the contextual suggestion track suffered from using dynamic collections and a shallow pool depth. The main innovations at TREC 2016 are the following.  ...  Acknowledgments We thank all participants and the many volunteers who contributed to the test collections built over the last five years of the TREC Contextual Suggestion Track.  ... 
dblp:conf/trec/HashemiKKCV16 fatcat:lpb6ir3gwnec7ozqjnvht3xnwm

Context Visualization for Social Bookmark Management [article]

Lilian Weng, Filippo Menczer
2012 arXiv   pre-print
, combined with the tag cloud.  ...  Unlike the interfaces of traditional social tagging tools, which usually display information in a list view, GalViz visualizes tags, resources, social links, and social context in an interactive network  ...  Users are therefore provided with contextual maps of semantic relationships of a tag or Web page in terms of related tags and pages.  ... 
arXiv:1211.6799v1 fatcat:lywl7clgp5bsjbsa5bvhmntzba

Keyword Search over Data Service Integration for Accurate Results

Vidmantas Zemleris, Valentin Kuznetsov, Robert Gwadera
2014 Journal of Physics, Conference Series  
Virtual data integration provides a coherent interface for querying heterogeneous data sources (e.g., web services, proprietary systems) with minimum upfront effort.  ...  Virtual data integration provides a coherent interface for querying heterogeneous data sources (e.g., web services, proprietary systems) with minimum upfront effort.  ...  Future challenges may include answering the queries over much larger number of data tables and data services, and answering the more complex queries than considered by us.  ... 
doi:10.1088/1742-6596/513/3/032106 fatcat:fsb5heshznefvarezxblyxhahi

Constructing folksonomies by integrating structured metadata

Anon Plangprasopchok, Kristina Lerman, Lise Getoor
2010 Proceedings of the 19th international conference on World wide web - WWW '10  
Our approach clusters similar hierarchies using their structure and tag statistics, then incrementally weaves them into a deeper, bushier tree.  ...  Our empirical results suggest that the proposed approach improves upon the state-of-the-art folksonomy learning method.  ...  For each leaf of the initial sapling, we use the leaf name to retrieve all other saplings whose roots are similar to the name.  ... 
doi:10.1145/1772690.1772856 dblp:conf/www/PlangprasopchokLG10 fatcat:uynkwd3qpva5lp7ekehrs7hvli

A Factored Relevance Model for Contextual Point-of-Interest Recommendation

Anirban Chakraborty, Debasis Ganguly, Annalina Caputo, Séamus Lawless
2019 Proceedings of the 2019 ACM SIGIR International Conference on Theory of Information Retrieval - ICTIR '19  
The challenge of providing personalized and contextually appropriate recommendations to a user is faced in a range of use-cases, e.g., recommendations for movies, places to visit, articles to read etc.  ...  Our experiments are conducted on the TREC contextual suggestion (TREC-CS) 2016 dataset.  ...  This work was supported by the ADAPT Centre for Digital Content Technology, funded under the Science Foundation Ireland Research Centres Programme (Grant 13/RC/2106) and is co-funded under the European  ... 
doi:10.1145/3341981.3344230 dblp:conf/ictir/ChakrabortyGCL19 fatcat:7l6xt2jgbvfejkffjgi7rmbp6e

An approach to enrich users' personomy using the recommendation of semantic tags

Sérgio R. P. da Silva, Marcelo R. Borth, Josiane M. P. Ferreira, Valéria D. Feltrim
2012 Journal of the Brazilian Computer Society  
The use of the Web resource helps to solve the cold start problem, and the recommendation of more contextualized and personalized tags helps to develop a bet-A previous version of this paper appeared at  ...  Our approach combines three sources of information for selecting the recommended tags: the Web resource been categorized, the tagging-based system folksonomy and the user personomy.  ...  Acknowledgements Our thanks to CAPES for the scholarship granted to Marcelo Rafael Borth during his Master degree from which this paper is a result.  ... 
doi:10.1007/s13173-011-0055-1 fatcat:wflooxbs3rfdbdkir4nbqegzcq

Multiple coordinated views for searching and navigating Web content repositories

Alexander Hubmann-Haidvogel, Arno Scharl, Albert Weichselbraun
2009 Information Sciences  
Currently, the system synchronizes information landscapes, domain ontologies, geographic maps, tag clouds and just-in-time information retrieval agents that suggest similar topics and nearby locations.  ...  controlled vocabulary for structuring the stored information.  ...  The authors wish to thank Arinya Eller for proof-reading the manuscript.  ... 
doi:10.1016/j.ins.2009.01.030 fatcat:6mi6cvgzabfhfdfgylk6ks43eu

Image understanding and the web: a state-of-the-art review

Fariza Fauzi, Mohammed Belkhatir
2014 Journal of Intelligent Information Systems  
Such characterization allows for understanding the image content and is crucial in important Web-based tasks such as image indexing and retrieval.  ...  contextual information in Web pages, we are aware that the unpredictable quality of the contextual information is a major limiting factor.  ...  Thus, we suggest an automatic extraction algorithm that is able to partition the Web page according to the defined boundaries of the contextual information for each image on a Web page.  ... 
doi:10.1007/s10844-014-0323-6 fatcat:ye44hw6oczf6vo7fp4ovh2k5nm

Introducing Various Semantic Models for Amharic: Experimentation and Evaluation with Multiple Tasks and Datasets

Seid Muhie Yimam, Abinew Ali Ayele, Gopalakrishnan Venkatesh, Ibrahim Gashaw, Chris Biemann
2021 Future Internet  
Furthermore, models based on contextual embeddings from FLAIR and RoBERTa perform better than word2Vec models for the NER and POS tagging tasks.  ...  Moreover, we employ these models for different NLP tasks and study their impact. We find that newly-trained models perform better than pre-trained multilingual models.  ...  For existing resources, we have indicated our contributions. * indicated corpus we have gathered from the web using the Scrapy (https://scrapy.org/ (accessed on 24 October 2021)) open source and collaborative  ... 
doi:10.3390/fi13110275 fatcat:osrgco66ebg6fdlvo2fevqycdq

Location-aware music recommendation using auto-tagging and hybrid matching

Marius Kaminskas, Francesco Ricci, Markus Schedl
2013 Proceedings of the 7th ACM conference on Recommender systems - RecSys '13  
We show that our approach can be scaled up using a novel music auto-tagging technique and we compare it in a live user study to: two non-hybrid solutions, either based on tags or on semantic relations;  ...  The suggested hybrid approach combines two techniques -one based on representing both POIs and music with tags, and the other based on the knowledge of the semantic relations between the two types of items  ...  A similar approach is suggested in [13] for auto-tagging artists.  ... 
doi:10.1145/2507157.2507180 dblp:conf/recsys/KaminskasRS13 fatcat:jrou7wan2bf4vfozaqhoj44v5a

Can Global Visual Features Improve Tag Recommendation for Image Annotation?

Mathias Lux, Arthur Pitman, Oge Marques
2010 Future Internet  
., in the form of tags, photos are difficult to find and organize. In this paper, we describe a system that recommends tags for image annotation.  ...  We present results from experiments conducted using photos and metadata sourced from the Flickr photo website that suggest that the use of visual features improves the mean average precision (MAP) of the  ...  The tags are suggested by weighing them proportionally to how often they were used on similar documents.  ... 
doi:10.3390/fi2030341 fatcat:3oofufzkuvhppdfwx7ep6atf6y

Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and Datasets [article]

Seid Muhie Yimam and Abinew Ali Ayele and Gopalakrishnan Venkatesh and Chris Biemann
2020 arXiv   pre-print
The models are build using word2Vec embeddings, distributional thesaurus (DT), contextual embeddings, and DT embeddings obtained via network embedding algorithms.  ...  Moreover, we employ these models for different NLP tasks and investigate their impact. We find that newly trained models perform better than pre-trained multilingual models.  ...  words generated from the AmDT, AmWord2Vec, and two contextualized suggestions from AmRoBERTa for the word ትርፍ.Columns AmRoBERTaS1 and AmRoBER-TaS2 show the the contextual suggestion for the <mask> word  ... 
arXiv:2011.01154v1 fatcat:gajakvelavgq7jcpshirouton4

Boosting Venue Page Rankings for Contextual Retrieval-Georgetown at TREC 2013 Contextual Suggestion Track

Jiyun Luo, Hui Yang
2013 Text Retrieval Conference  
Since the Open Web is not used in our submissions, the task is essentially a retrieval task instead of a result merging task.  ...  Therefore, large portions of the retrieved documents are not suitable as answers for contextual suggestion.  ...  All HTML tags are removed. Submissions and Results We submit two runs to TREC 2013 Contextual Suggestion Track, namely BOW_V17 and BOW_V18. They are similar runs.  ... 
dblp:conf/trec/LuoY13 fatcat:xnw5y7oiufc7lm7isjt3n2t3ay

MusiClef: Multimodal Music Tagging Task [chapter]

Nicola Orio, Cynthia C. S. Liem, Geoffroy Peeters, Markus Schedl
2012 Lecture Notes in Computer Science  
Mu-siClef deals with a concrete use case, encourages multimodal approaches based on these, and strives for transparency of results as much as possible.  ...  Transparency is encouraged at several levels and stages, from the feature extraction procedure up to the evaluation phase, in which a dedicated categorization of ground truth tags will be used to deepen  ...  Acknowledgments The authors would like to thank David Rizo, of the University of Alicante, for his support in starting the MusiCLEF initiative.  ... 
doi:10.1007/978-3-642-33247-0_5 fatcat:hfzfk3tywvdnvl2og7vsnnb4nm
« Previous Showing results 1 — 15 out of 16,244 results