Increasingly user-generated content is being utilised as a source of information, however each individual piece of content tends to contain low levels of information. In addition, such information tends to be informal and imperfect in nature; containing imprecise, subjective, ambiguous expressions. However the content does not have to be interpreted in isolation as it is linked, either explicitly or implicitly, to a network of interrelated content; it may be grouped or tagged with similar content, comments may be added by other users or it may be related to other content posted at the same time or by the same author or members of the author's social network. This paper generally examines how ambiguous concepts within user-generated content can be assigned a specific/formal meaning by considering the expanding context of the information, i.e. other information contained within directly or indirectly related content, and specifically considers the issue of toponym resolution of locations.

@inproceedings{ireson2010toponym, author = {Ireson, Neil and Ciravegna, Fabio}, title = {Toponym Resolution in Social Media.}, editor = {Patel-Schneider, Peter F. and Pan, Yue and Hitzler, Pascal and Mika, Peter and Zhang, Lei and Pan, Jeff Z. and Horrocks, Ian and Glimm, Birte}, booktitle = {#iswc2010#}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2010}, volume = {6496}, pages = {370-385}, url = {http://dblp.uni-trier.de/db/conf/semweb/iswc2010-1.html#IresonC10}, isbn = {978-3-642-17745-3}, keywords = {ol_web2.0, ontology_learning, social_media, toponym, disambiguation, methods_concepts}, abstract = {Increasingly user-generated content is being utilised as a source of information, however each individual piece of content tends to contain low levels of information. In addition, such information tends to be informal and imperfect in nature; containing imprecise, subjective, ambiguous expressions. However the content does not have to be interpreted in isolation as it is linked, either explicitly or implicitly, to a network of interrelated content; it may be grouped or tagged with similar content, comments may be added by other users or it may be related to other content posted at the same time or by the same author or members of the author's social network. This paper generally examines how ambiguous concepts within user-generated content can be assigned a specific/formal meaning by considering the expanding context of the information, i.e. other information contained within directly or indirectly related content, and specifically considers the issue of toponym resolution of locations.} }

%0 = inproceedings %A = Ireson, Neil and Ciravegna, Fabio %B = #iswc2010# %D = 2010 %I = Springer %T = Toponym Resolution in Social Media. %U = http://dblp.uni-trier.de/db/conf/semweb/iswc2010-1.html#IresonC10

Collaborative tagging services (folksonomies) have been among the stars of theWeb 2.0 era. They allow their users to label diverse resources with freely chosen keywords (tags). Our studies of two real-world folksonomies unveil that individual users develop highly personalized vocabularies of tags. While these meet individual needs and preferences, the considerable differences between personal tag vocabularies (personomies) impede services such as social search or customized tag recommendation. In this paper, we introduce a novel user-centric tag model that allows us to derive mappings between personal tag vocabularies and the corresponding folksonomies. Using these mappings, we can infer the meaning of user-assigned tags and can predict choices of tags a user may want to assign to new items. Furthermore, our translational approach helps in reducing common problems related to tag ambiguity, synonymous tags, or multilingualism. We evaluate the applicability of our method in tag recommendation and tag-based social search. Extensive experiments show that our translational model improves the prediction accuracy in both scenarios.

@inproceedings{wetzker2010i, author = {Wetzker, Robert and Zimmermann, Carsten and Bauckhage, Christian and Albayrak, Sahin}, title = {I tag, you tag: translating tags for advanced user models.}, editor = {Davison, Brian D. and Suel, Torsten and Craswell, Nick and Liu, Bing}, booktitle = {WSDM}, publisher = {ACM}, year = {2010}, pages = {71-80}, url = {http://dblp.uni-trier.de/db/conf/wsdm/wsdm2010.html#WetzkerZBA10}, isbn = {978-1-60558-889-6}, keywords = {tag_translation, tagging, ol_web2.0, methods_synonyms, disambiguation}, abstract = {Collaborative tagging services (folksonomies) have been among the stars of theWeb 2.0 era. They allow their users to label diverse resources with freely chosen keywords (tags). Our studies of two real-world folksonomies unveil that individual users develop highly personalized vocabularies of tags. While these meet individual needs and preferences, the considerable differences between personal tag vocabularies (personomies) impede services such as social search or customized tag recommendation. In this paper, we introduce a novel user-centric tag model that allows us to derive mappings between personal tag vocabularies and the corresponding folksonomies. Using these mappings, we can infer the meaning of user-assigned tags and can predict choices of tags a user may want to assign to new items. Furthermore, our translational approach helps in reducing common problems related to tag ambiguity, synonymous tags, or multilingualism. We evaluate the applicability of our method in tag recommendation and tag-based social search. Extensive experiments show that our translational model improves the prediction accuracy in both scenarios.} }

%0 = inproceedings %A = Wetzker, Robert and Zimmermann, Carsten and Bauckhage, Christian and Albayrak, Sahin %B = WSDM %D = 2010 %I = ACM %T = I tag, you tag: translating tags for advanced user models. %U = http://dblp.uni-trier.de/db/conf/wsdm/wsdm2010.html#WetzkerZBA10

The availability of tag-based user-generated content for a variety of Web resources (music, photos, videos, text, etc.) has largely increased in the last years. Users can assign tags freely and then use them to share and retrieve information. However, tag-based sharing and retrieval is not optimal due to the fact that tags are plain text labels without an explicit or formal meaning, and hence polysemy and synonymy should be dealt with appropriately. To ameliorate these problems, we propose a context-based tag disambiguation algorithm that selects the meaning of a tag among a set of candidate DBpedia entries, using a common information retrieval similarity measure. The most similar DBpedia en-try is selected as the one representing the meaning of the tag. We describe and analyze some preliminary results, and discuss about current challenges in this area.

@inproceedings{garcia2009preliminary, author = {Garcia, Andres and Szomszor, Martin and Alani, Harith and Corcho, Oscar}, title = {Preliminary Results in Tag Disambiguation using DBpedia}, booktitle = {Knowledge Capture (K-Cap'09) - First International Workshop on Collective Knowledge Capturing and Representation - CKCaR'09}, year = {2009}, url = {http://eprints.ecs.soton.ac.uk/17792/}, keywords = {ol_web2.0, ontology_learning, disambiguation}, abstract = {The availability of tag-based user-generated content for a variety of Web resources (music, photos, videos, text, etc.) has largely increased in the last years. Users can assign tags freely and then use them to share and retrieve information. However, tag-based sharing and retrieval is not optimal due to the fact that tags are plain text labels without an explicit or formal meaning, and hence polysemy and synonymy should be dealt with appropriately. To ameliorate these problems, we propose a context-based tag disambiguation algorithm that selects the meaning of a tag among a set of candidate DBpedia entries, using a common information retrieval similarity measure. The most similar DBpedia en-try is selected as the one representing the meaning of the tag. We describe and analyze some preliminary results, and discuss about current challenges in this area.} }

%0 = inproceedings %A = Garcia, Andres and Szomszor, Martin and Alani, Harith and Corcho, Oscar %B = Knowledge Capture (K-Cap'09) - First International Workshop on Collective Knowledge Capturing and Representation - CKCaR'09 %D = 2009 %T = Preliminary Results in Tag Disambiguation using DBpedia %U = http://eprints.ecs.soton.ac.uk/17792/

Tagging is one of the most popular services in Web 2.0. As a special form of tagging, social tagging is done collaboratively by many users, which forms a so-called folksonomy. As tagging has become widespread on the Web, the tag vocabulary is now very informal, uncontrolled, and personalized. For this reason, many tags are unfamiliar and ambiguous to users so that they fail to understand the meaning of each tag. In this paper, we propose a tag sense disambiguating method, called Tag Sense Disambiguation (TSD), which works in the social tagging environment. TSD can be applied to the vocabulary of social tags, thereby enabling users to understand the meaning of each tag through Wikipedia. To find the correct mappings from del.icio.us tags to Wikipedia articles, we define the Local )eighbor tags, the Global )eighbor tags, and finally the )eighbor tags that would be the useful keywords for disambiguating the sense of each tag based on the tag co-occurrences. The automatically built mappings are reasonable in most cases. The experiment shows that TSD can find the correct mappings with high accuracy.

@inproceedings{lee2009tag, author = {Lee, Kangpyo and Kim, Hyunwoo and Shin, Hyopil and Kim, Hyoung-Joo}, title = {Tag Sense Disambiguation for Clarifying the Vocabulary of Social Tags}, booktitle = {CSE}, publisher = {IEEE Computer Society}, year = {2009}, pages = {729--734}, url = {http://dx.doi.org/10.1109/CSE.2009.454}, keywords = {disambiguation, tag_sense_disambiguation, tagging, ol_web2.0}, abstract = {Tagging is one of the most popular services in Web 2.0. As a special form of tagging, social tagging is done collaboratively by many users, which forms a so-called folksonomy. As tagging has become widespread on the Web, the tag vocabulary is now very informal, uncontrolled, and personalized. For this reason, many tags are unfamiliar and ambiguous to users so that they fail to understand the meaning of each tag. In this paper, we propose a tag sense disambiguating method, called Tag Sense Disambiguation (TSD), which works in the social tagging environment. TSD can be applied to the vocabulary of social tags, thereby enabling users to understand the meaning of each tag through Wikipedia. To find the correct mappings from del.icio.us tags to Wikipedia articles, we define the Local )eighbor tags, the Global )eighbor tags, and finally the )eighbor tags that would be the useful keywords for disambiguating the sense of each tag based on the tag co-occurrences. The automatically built mappings are reasonable in most cases. The experiment shows that TSD can find the correct mappings with high accuracy.} }

%0 = inproceedings %A = Lee, Kangpyo and Kim, Hyunwoo and Shin, Hyopil and Kim, Hyoung-Joo %B = CSE %D = 2009 %I = IEEE Computer Society %T = Tag Sense Disambiguation for Clarifying the Vocabulary of Social Tags %U = http://dx.doi.org/10.1109/CSE.2009.454

Blog users enjoy tagging for better document organization, while ambiguity in tags leads to inaccuracy in tag-based applications, such as retrieval, visualization or trend discovery. The dynamic nature of tag meanings makes current word sense disambiguation(WSD) methods not applicable. In this paper, we propose an unsupervised method for disambiguating tags in blogs. We first cluster the tags by their context words using Spectral Clustering. Then we compare a tag with these clusters to find the most suitable meaning. We use Normalized Google Distance to measure word similarity, which can be computed by querying search engines, thus reflects the up-to-date meaning of words. No human labeling efforts or dictionary needed in our method. Evaluation using crawled blog data showed a promising micro average precision of 0.842.

@inproceedings{si2009disambiguating, author = {Si, Xiance and Sun, Maosong}, title = {Disambiguating Tags in Blogs}, editor = {Matousek, Václav and Mautner, Pavel}, booktitle = {TSD}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, year = {2009}, volume = {5729}, pages = {139--146}, url = {http://dx.doi.org/10.1007/978-3-642-04208-9}, isbn = {978-3-642-04207-2}, keywords = {tag_sense_disambigution, ol_web2.0, disambiguation, data_blogs}, abstract = {Blog users enjoy tagging for better document organization, while ambiguity in tags leads to inaccuracy in tag-based applications, such as retrieval, visualization or trend discovery. The dynamic nature of tag meanings makes current word sense disambiguation(WSD) methods not applicable. In this paper, we propose an unsupervised method for disambiguating tags in blogs. We first cluster the tags by their context words using Spectral Clustering. Then we compare a tag with these clusters to find the most suitable meaning. We use Normalized Google Distance to measure word similarity, which can be computed by querying search engines, thus reflects the up-to-date meaning of words. No human labeling efforts or dictionary needed in our method. Evaluation using crawled blog data showed a promising micro average precision of 0.842.} }

%0 = inproceedings %A = Si, Xiance and Sun, Maosong %B = TSD %D = 2009 %I = Springer %T = Disambiguating Tags in Blogs %U = http://dx.doi.org/10.1007/978-3-642-04208-9

At present tagging is experimenting a great diffusion as the most adopted way to collaboratively classify resources over the Web. In this paper, after a detailed analysis of the attempts made to improve the organization and structure of tagging systems as well as the usefulness of this kind of social data, we propose and evaluate the Tag Disambiguation Algorithm, mining del.icio.us data. It allows to easily semantify the tags of the users of a tagging service: it automatically finds out for each tag the related concept of Wikipedia in order to describe Web resources through senses. On the basis of a set of evaluation tests, we analyze all the advantages of our sense-based way of tagging, proposing new methods to keep the set of users tags more consistent or to classify the tagged resources on the basis of Wikipedia categories, YAGO classes or Wordnet synsets. We discuss also how our semanitified social tagging data are strongly linked to DBPedia and the datasets of the Linked Data community. 1

@inproceedings{tesconi2008semantify, author = {Tesconi, Maurizio and Ronzano, Francesco and Marchetti, Andrea and Minutoli, Salvatore}, title = {Semantify del.icio.us: Automatically Turn your Tags into Senses}, booktitle = {Proceedings of the Workshop Social Data on the Web (SDoW2008)}, year = {2008}, url = {http://CEUR-WS.org/Vol-405/paper8.pdf}, keywords = {ol_web2.0, ontology_learning, toread, toread_dbe, disambiguation, tag_concept_mapping}, abstract = {At present tagging is experimenting a great diffusion as the most adopted way to collaboratively classify resources over the Web. In this paper, after a detailed analysis of the attempts made to improve the organization and structure of tagging systems as well as the usefulness of this kind of social data, we propose and evaluate the Tag Disambiguation Algorithm, mining del.icio.us data. It allows to easily semantify the tags of the users of a tagging service: it automatically finds out for each tag the related concept of Wikipedia in order to describe Web resources through senses. On the basis of a set of evaluation tests, we analyze all the advantages of our sense-based way of tagging, proposing new methods to keep the set of users tags more consistent or to classify the tagged resources on the basis of Wikipedia categories, YAGO classes or Wordnet synsets. We discuss also how our semanitified social tagging data are strongly linked to DBPedia and the datasets of the Linked Data community. 1} }

%0 = inproceedings %A = Tesconi, Maurizio and Ronzano, Francesco and Marchetti, Andrea and Minutoli, Salvatore %B = Proceedings of the Workshop Social Data on the Web (SDoW2008) %D = 2008 %T = Semantify del.icio.us: Automatically Turn your Tags into Senses %U = http://CEUR-WS.org/Vol-405/paper8.pdf

Roget’s Thesaurus is a lexical resource which groups terms by semantic relatedness. It is Roget’s shortcoming that the relations are ambiguous, in that it does not name them; it only shows that there is a relation between terms. Our work focuses on disambiguating hypernym relations within Roget’s Thesaurus. Several techniques of identifying hypernym relations are compared and contrasted in this paper, and a total of over 50,000 hypernym relations have been disambiguated within Roget’s. Human judges have evaluated the quality of our disambiguation techniques, and we have demonstrated on several applications the usefulness of the disambiguated relations.

@incollection{kennedy2007disambiguating, author = {Kennedy, Alistair and Szpakowicz, Stanistaw}, title = {Disambiguating Hypernym Relations for <i>Roget’s</i> Thesaurus}, editor = {Matoušek, Václav and Mautner, Pavel}, booktitle = {Text, Speech and Dialogue}, series = {Lecture Notes in Computer Science}, publisher = {Springer}, address = {Berlin / Heidelberg}, year = {2007}, volume = {4629}, pages = {66-75}, url = {http://dx.doi.org/10.1007/978-3-540-74628-7_11}, doi = {10.1007/978-3-540-74628-7_11}, keywords = {disambiguation, roget, thesaurus}, abstract = {Roget’s Thesaurus is a lexical resource which groups terms by semantic relatedness. It is Roget’s shortcoming that the relations are ambiguous, in that it does not name them; it only shows that there is a relation between terms. Our work focuses on disambiguating hypernym relations within Roget’s Thesaurus. Several techniques of identifying hypernym relations are compared and contrasted in this paper, and a total of over 50,000 hypernym relations have been disambiguated within Roget’s. Human judges have evaluated the quality of our disambiguation techniques, and we have demonstrated on several applications the usefulness of the disambiguated relations.} }

%0 = incollection %A = Kennedy, Alistair and Szpakowicz, Stanistaw %B = Text, Speech and Dialogue %C = Berlin / Heidelberg %D = 2007 %I = Springer %T = Disambiguating Hypernym Relations for <i>Roget’s</i> Thesaurus %U = http://dx.doi.org/10.1007/978-3-540-74628-7_11

Collaborative tagging systems are becoming very popular recently. Web users use freely-chosen tags to describe shared resources, resulting in a folksonomy. One problem of folksonomies is that tags which appear in the same form may carry multiple meanings and represent different concepts. As this kind of tags are ambiguous, the precisions in both description and retrieval of the shared resources are reduced. We attempt to develop effective methods to disambiguate tags by studying the tripartite structure of folksonomies. This paper describes the network analysis techniques that we employ to discover clusters of nodes in networks and the algorithm for tag disambiguation. Experiments show that the method is very effective in performing the task.

@inproceedings{auyeung2007tag, author = {man Au Yeung, Ching and Gibbins, Nicholas and Shadbolt, Nigel}, title = {Tag Meaning Disambiguation through Analysis of Tripartite Structure of Folksonomies}, booktitle = {Web Intelligence/IAT Workshops}, publisher = {IEEE}, year = {2007}, pages = {3--6}, url = {http://dx.doi.org/10.1109/WIIATW.2007.4427527}, keywords = {disambiguation, folksonomies, tag_sense_disambigution, ol_web2.0, methods_concepts}, abstract = {Collaborative tagging systems are becoming very popular recently. Web users use freely-chosen tags to describe shared resources, resulting in a folksonomy. One problem of folksonomies is that tags which appear in the same form may carry multiple meanings and represent different concepts. As this kind of tags are ambiguous, the precisions in both description and retrieval of the shared resources are reduced. We attempt to develop effective methods to disambiguate tags by studying the tripartite structure of folksonomies. This paper describes the network analysis techniques that we employ to discover clusters of nodes in networks and the algorithm for tag disambiguation. Experiments show that the method is very effective in performing the task.} }

%0 = inproceedings %A = man Au Yeung, Ching and Gibbins, Nicholas and Shadbolt, Nigel %B = Web Intelligence/IAT Workshops %D = 2007 %I = IEEE %T = Tag Meaning Disambiguation through Analysis of Tripartite Structure of Folksonomies %U = http://dx.doi.org/10.1109/WIIATW.2007.4427527

@inproceedings{widdows2002graph, author = {Widdows, Dominic and Dorow, Beate}, title = {A Graph Model for Unsupervised Lexical Acquisition}, booktitle = {COLING}, year = {2002}, keywords = {disambiguation, ontology_learning, tag, unsupervised} }

%0 = inproceedings %A = Widdows, Dominic and Dorow, Beate %B = COLING %D = 2002 %T = A Graph Model for Unsupervised Lexical Acquisition