%0 Conference Paper %1 Shen:2013:LNE:2487575.2487686 %A Shen, Wei %A Wang, Jianyong %A Luo, Ping %A Wang, Min %B Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining %C New York, NY, USA %D 2013 %I ACM %K disambiguation linking namedentity phdproposal %P 68--76 %R 10.1145/2487575.2487686 %T Linking Named Entities in Tweets with Knowledge Base via User Interest Modeling %U http://doi.acm.org/10.1145/2487575.2487686 %X Twitter has become an increasingly important source of information, with more than 400 million tweets posted per day. The task to link the named entity mentions detected from tweets with the corresponding real world entities in the knowledge base is called tweet entity linking. This task is of practical importance and can facilitate many different tasks, such as personalized recommendation and user interest discovery. The tweet entity linking task is challenging due to the noisy, short, and informal nature of tweets. Previous methods focus on linking entities in Web documents, and largely rely on the context around the entity mention and the topical coherence between entities in the document. However, these methods cannot be effectively applied to the tweet entity linking task due to the insufficient context information contained in a tweet. In this paper, we propose KAURI, a graph-based framework to collectively link all the named entity mentions in all tweets posted by a user via modeling the user's topics of interest. Our assumption is that each user has an underlying topic interest distribution over various named entities. KAURI integrates the intra-tweet local information with the inter-tweet user interest information into a unified graph-based framework. We extensively evaluated the performance of KAURI over manually annotated tweet corpus, and the experimental results show that KAURI significantly outperforms the baseline methods in terms of accuracy, and KAURI is efficient and scales well to tweet stream. %@ 978-1-4503-2174-7

@inproceedings{Shen:2013:LNE:2487575.2487686, abstract = {Twitter has become an increasingly important source of information, with more than 400 million tweets posted per day. The task to link the named entity mentions detected from tweets with the corresponding real world entities in the knowledge base is called tweet entity linking. This task is of practical importance and can facilitate many different tasks, such as personalized recommendation and user interest discovery. The tweet entity linking task is challenging due to the noisy, short, and informal nature of tweets. Previous methods focus on linking entities in Web documents, and largely rely on the context around the entity mention and the topical coherence between entities in the document. However, these methods cannot be effectively applied to the tweet entity linking task due to the insufficient context information contained in a tweet. In this paper, we propose KAURI, a graph-based framework to collectively link all the named entity mentions in all tweets posted by a user via modeling the user's topics of interest. Our assumption is that each user has an underlying topic interest distribution over various named entities. KAURI integrates the intra-tweet local information with the inter-tweet user interest information into a unified graph-based framework. We extensively evaluated the performance of KAURI over manually annotated tweet corpus, and the experimental results show that KAURI significantly outperforms the baseline methods in terms of accuracy, and KAURI is efficient and scales well to tweet stream.}, acmid = {2487686}, added-at = {2015-01-05T23:25:05.000+0100}, address = {New York, NY, USA}, author = {Shen, Wei and Wang, Jianyong and Luo, Ping and Wang, Min}, biburl = {https://www.bibsonomy.org/bibtex/2c0fc13cbd222bec66931a49b43665144/asmelash}, booktitle = {Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, description = {Linking named entities in Tweets with knowledge base via user interest modeling}, doi = {10.1145/2487575.2487686}, interhash = {b9de132612aa1b58d1e5cebe03b19d51}, intrahash = {c0fc13cbd222bec66931a49b43665144}, isbn = {978-1-4503-2174-7}, keywords = {disambiguation linking namedentity phdproposal}, location = {Chicago, Illinois, USA}, numpages = {9}, pages = {68--76}, publisher = {ACM}, series = {KDD '13}, timestamp = {2015-01-05T23:25:05.000+0100}, title = {Linking Named Entities in Tweets with Knowledge Base via User Interest Modeling}, url = {http://doi.acm.org/10.1145/2487575.2487686}, year = 2013 }