Filters








2,804 Hits in 5.1 sec

Research on event perception based on geo-tagged social media data

Ruoxin Zhu, Chenyu Zuo, Diao Lin
2019 Proceedings of the ICA  
This paper provides an overview of event study based on geo-tagged social media data. Firstly, we introduce the event model and the characteristics of social media data.  ...  How to perceive an event through social media data has triggered a series of researches. Currently, we can find when, where what happened and induced impact based on geo-tagged social media data.  ...  The opinion mining from geo-tagged social media data is consistent with actual public opinion, showing that it is an effective way to understand social attitudes toward event through social media.  ... 
doi:10.5194/ica-proc-2-157-2019 fatcat:i2vo6okebvfgjl5xuiid235a3m

Towards Universal Semantic Tagging [article]

Lasha Abzianidze, Johan Bos
2017 arXiv   pre-print
As a part of the application, we annotate a small corpus with the semantic tags and present new baseline result for universal semantic tagging.  ...  We present the initial version of the semantic tagset and show that (a) the tags provide semantically fine-grained information, and (b) they are suitable for cross-lingual semantic parsing.  ...  Table 1 : 1 The Universal Semantic Tagset v0.7: 73 sem-tags grouped into 13 meta-tags. The sem-tags are accompanied with the examples where several highly ambiguous tokens come with a context.  ... 
arXiv:1709.10381v1 fatcat:7drjydrkcfgw7huzwfc4nazwye

A Survey of Volunteered Open Geo-Knowledge Bases in the Semantic Web [chapter]

Andrea Ballatore, David C. Wilson, Michela Bertolotto
2013 Intelligent Systems Reference Library  
Over the past decade, rapid advances in web technologies, coupled with innovative models of spatial data collection and consumption, have generated a robust growth in geo-referenced information, resulting  ...  Particular attention is devoted to the crucial issue of the quality of geo-knowledge bases, as well as of crowdsourced data.  ...  Acknowledgements The research presented in this paper was funded by a Strategic Research Cluster grant (07/SRC/I1168) by Science Foundation Ireland under the National Development Plan.  ... 
doi:10.1007/978-3-642-37688-7_5 fatcat:i72rmxk36fbnrmnrdpkmccrbfu

Learning Visual Contexts for Image Annotation From Flickr Groups

Adrian Ulges, Marcel Worring, Thomas Breuel
2011 IEEE transactions on multimedia  
ACKNOWLEDGMENT This work was supported by the German Research Foundation (DFG), project MOONVID (BR 2517/1-1). We want to thank R.  ...  problem requiring quality to be driven closer towards the level of human annotations.  ...  "), a context-specific model trained on the Flickr group "Rome Pictures" can identify the correct tag to be "park". information for training, annotation systems have been shown to perform autonomous visual  ... 
doi:10.1109/tmm.2010.2101051 fatcat:v6brsvknxbeulfs4c4p6ulmtz4

Globalization and the erosion of geo-ethnic checkpoints: evolving signal-boundary systems at the edge of chaos

Chris Girard
2019 Evolutionary and Institutional Economics Review  
Centered on these three dimensions, a proposed evolutionary informatics model roots ethnic and racial cleavages in zero-sum contests over rivalrous resources within geophysical sites.  ...  This uncoupling from physical location is driven by cybernetic parallelism in complex adaptive systems: diverse and independent agents learning from their mutual exchange of signals.  ...  The consequent zero-sum dynamic may be reinvigorating geo-ethnic cleavages. Complex systems can devolve toward greater simplicity, as evidenced by Nazi Germany (see Weidlich 2000) .  ... 
doi:10.1007/s40844-019-00152-2 fatcat:sydvnfiwo5ehpcnvqgepbslrca

NATO Trident Juncture on Twitter: Public Discussion

William Frankenstein, Binxuan Huang, Kathleen M. Carley
2016 Social Science Research Network  
The geo-tagged tweets we collected are either tagged with a longitude/latitude coordinates or associated with a place defined as a small geographic box like "Roma": 12.234427 , 41.655874 12.855864 , 42.140959  ...  Sentiment Trends towards NATO To determine the attitudes behind each tweet(positive or negative), we developed a sentiment classifier based on VADER [2] which is a rule-based sentiment analysis model for  ...  regarding NATO • The more saturated the blue, the more positive • The more saturated the red, the more negative • Only tweets with geo-tags (latitudes and longitudes) are used. • All geo-tagged tweets  ... 
doi:10.2139/ssrn.2720320 fatcat:yrtzhiyuufd5tj4b6kbgqsorre

On the Linguistic Representational Power of Neural Machine Translation Models

Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Hassan Sajjad, James Glass
2020 Computational Linguistics  
Our data-driven, quantitative evaluation illuminates important aspects in NMT models and their ability to capture various linguistic phenomena.  ...  We show that deep NMT models trained in an end-to-end fashion, without being provided any direct supervision during the training process, learn a non-trivial amount of linguistic information.  ...  Unlike traditional systems that contain specialized modules carrying specific sub-tasks, neural MT (NMT) systems train one large network, optimized toward the overall task.  ... 
doi:10.1162/coli_a_00367 fatcat:5xux2ogrbfhozncsgkneuaz2k4

On the Linguistic Representational Power of Neural Machine Translation Models [article]

Yonatan Belinkov, Nadir Durrani, Fahim Dalvi, Hassan Sajjad, James Glass
2019 arXiv   pre-print
We show that deep NMT models learn a non-trivial amount of linguistic information.  ...  Our data-driven, quantitative evaluation illuminates important aspects in NMT models and their ability to capture various linguistic phenomena.  ...  Models for Machine Translation Between Closely-Related Languages.  ... 
arXiv:1911.00317v1 fatcat:uncw5nmpefhrpo7jtverg6c7qy

Visual Overlay on OpenStreetMap Data to Support Spatial Exploration of Urban Environments

Chandan Kumar, Wilko Heuten, Susanne Boll
2015 ISPRS International Journal of Geo-Information  
We report the end user acceptability and efficiency of the proposed system via usability studies and performance analysis comparison.  ...  In this work, we analyze the OSM data to classify the geo entities into consequential categories with facilities, landscape and land use distribution.  ...  We also thank Uwe Wilko Gruenefeld for his contributions in system prototyping and experiments.  ... 
doi:10.3390/ijgi4010087 fatcat:4bgpwx3dqvdtrcgix5pcnykmda

Linked open data to represent multilingual poetry collections. A proposal to solve interoperability issues between poetic repertoires

Elena González-Blanco, Gimena del Rio, Clara Martínez Cantón
2016 Zenodo  
It has been built on the model of the Spanish digital repertoire ReMetCa, but its aim is to be enlarg ed and improved in order to fit under every poetic system.  ...  Th is paper describes the creation of a poetic ontology in order to use it as a basis to link different databases and projects w orking on metrics and poetry.  ...  In 2012, the first author continued his research on OLiA in the context of PostDoc fellowship at the Information Sciences Institute of the University of Southern California funded by the German Academic  ... 
doi:10.5281/zenodo.2551595 fatcat:4nbzl534ebgnbort742fhfoqam

Visual Analysis and Knowledge Discovery for Text [chapter]

Christin Seifert, Vedran Sabol, Wolfgang Kienreich, Elisabeth Lex, Michael Granitzer
2013 Large-Scale Data Analytics  
Providing means for effectively accessing and exploring large textual data sets is a problem attracting the attention of text mining and information visualization experts alike.  ...  The German-language Brockhaus encyclopedia provides a visualization system which enables the visual navigation of article context.  ...  Figure 7 .6 shows a geo-spatial visualization of locations extracted from German news articles [28] .  ... 
doi:10.1007/978-1-4614-9242-9_7 fatcat:5ti6ubvuj5d5dhfjg6eyiyld6m

Linguistic Correlation Analysis: Discovering Salient Neurons in deepNLP models [article]

Nadir Durrani and Fahim Dalvi and Hassan Sajjad
2022 arXiv   pre-print
While a lot of work has been done in understanding representations learned within deep NLP models and what knowledge they capture, little attention has been paid towards individual neurons.  ...  We present a technique called as Linguistic Correlation Analysis to extract salient neurons in the model, with respect to any extrinsic property - with the goal of understanding how such a knowledge is  ...  Such an analysis can be potentially useful for not only debugging the systems for errors, but improving the design choices and system performance.  ... 
arXiv:2206.13288v1 fatcat:dsp4jxwvcjdylh4hdbxfruf22a

A Concrete Chinese NLP Pipeline

Nanyun Peng, Francis Ferraro, Mo Yu, Nicholas Andrews, Jay DeYoung, Max Thomas, Matthew R. Gormley, Travis Wolfe, Craig Harman, Benjamin Van Durme, Mark Dredze
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations  
We present a CONCRETE Chinese NLP Pipeline: an NLP stack built using a series of open source systems integrated based on the CONCRETE data schema.  ...  Our pipeline includes data ingest, word segmentation, part of speech tagging, parsing, named entity recognition, relation extraction and cross document coreference resolution.  ...  A National Science Foundation Graduate Research Fellowship, under 5 https://bitbucket.org/noandrews/phyloinf 6 https://github.com/hltcoe/quicklime 89 Grant No.  ... 
doi:10.3115/v1/n15-3018 dblp:conf/naacl/PengFYADTGWHDD15 fatcat:lhwx6zf3pjcmxgsmuaxrllwcdq

Systematic Evaluation of Social Recommendation Systems: Challenges and Future

Priyanka Rastogi, Dr. Vijendra
2016 International Journal of Advanced Computer Science and Applications  
Social Recommender System (SRS) exploits social contextual information in the form of social links of users, social tags, user-generated data that contain huge supplemental information about items or services  ...  The issue of information overload could be effectively managed with the help of intelligent system which is capable of proactively supervising the users in accessing relevant or useful information in a  ...  model in Social Tagging Systems (STS).  ... 
doi:10.14569/ijacsa.2016.070420 fatcat:wwvyumdr5ffohiphirbb3ycuoa

Extended Overview of CLEF HIPE 2020: Named Entity Processing on Historical Newspapers

Ehrmann, Romanello, Flückiger, Clematide
2020 Zenodo  
on historical newspapers in French, German and English.  ...  This paper presents an extended overview of the first edition of HIPE (Identifying Historical People, Places and other Entities), a pioneering shared task dedicated to the evaluation of named entity processing  ...  A state-of-the-art CRF layer was added on top in order to model the context dependencies between entity tags.  ... 
doi:10.5281/zenodo.4117566 fatcat:wyft6y2mbbfljoal4we5ibusa4
« Previous Showing results 1 — 15 out of 2,804 results