1,429 Hits in 8.6 sec

A Case Study of NLG from Multimedia Data Sources: Generating Architectural Landmark Descriptions

Simon Mille, Leo Wanner, Spyridon Symeonidis, Maria Rousi, Montserrat Marimon Felipe, Klearchos Stavrothanasopoul, Petros Alvanitopoulos, Roberto Carlini
2020 Zenodo  
In this paper, we present a pipeline system that generates architectural landmark descriptions using textual, visual and structured data.  ...  We show that thanks to the addition of other modalities, we can make the verbalisation of DBpedia triples more relevant and/or inspiratio  ...  and Information Technologies Institute -CERTH.  ... 
doi:10.5281/zenodo.4529236 fatcat:k36enq2vtfavnk3uyuwhb2oz4q

Summarization of UGC [chapter]

2014 Mining User Generated Content  
Acknowledgements: This work was supported by funding from the Engineering and Physical Sciences Research Council (grant EP/I004327/1).  ...  Similar methods have also been studied on Twitter data. [67] classify arbitrary tweets on the basis of positive, negative and neutral sentiment and then aggregate the overall sentiment.  ...  Summarising Very Short UGC As discussed in Section 14.3, summarising tweets and other kinds of short UGC (e.g. comments on a news or a video site) is a particularly challenging problem.  ... 
doi:10.1201/b16413-22 fatcat:6umoamubbjf53etlz2lyvvbtoa

From Hotel Reviews to City Similarities: A Unified Latent-Space Model

Luca Cagliero, Moreno La Quatra, Daniele Apiletti
2020 Electronics  
and the surrounding points of interests.  ...  A large portion of user-generated content published on the Web consists of opinions and reviews on products, services, and places in textual form.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/electronics9010197 fatcat:fnnwj2qfsrhfrkfjgdsumlwsh4

DBATES: DataBase of Audio features, Text, and visual Expressions in competitive debate Speeches [article]

Taylan K. Sen, Gazi Naven, Luke Gerstner, Daryl Bagley, Raiyan Abdul Baten, Wasifur Rahman, Kamrul Hasan, Kurtis G. Haut, Abdullah Mamun, Samiha Samrose, Anne Solbu, R. Eric Barnes (+2 others)
2021 arXiv   pre-print
We use these results to highlight the value of a multimodal dataset for studying competitive, collegiate debate.  ...  Feature sets were extracted from the visual (facial expression, gaze, and head pose), audio (PRAAT), and textual (word sentiment and linguistic category) modalities of raw video recordings of competitive  ...  The authors would like to thank the HWS debate team for their help. The first two authors should be considered co-first authors.  ... 
arXiv:2103.14189v1 fatcat:6xihupnaazenhja4iyfd73kb4u

Creative Map Studio: A Platform for Visual Analytics of Mental Maps

R.V. Chumakov, K.V. Ryabinin, K.I. Belousov, J. Duan
2021 Scientific Visualization  
The Creative Maps Studio web application provides a wide variety of drawing tools based on points, lines, and areas, which allow representing different objects on the map, such as cities, historical monuments  ...  After exporting, the expert can use SciVi and Semograph to perform visual analytics of map objects' properties, to handle maps' textual layers, and to classify the maps on the principles of the fuzzy set  ...  The basic element for comparison in these cases is a set of landmarks on the map. On a global scale, such landmarks can be, for example, settlements, state borders, seas, mountain ranges, etc.  ... 
doi:10.26583/sv.13.2.06 fatcat:pwej4en6rbazhpor6fg2u5arg4

A context-aware personalized travel recommendation system based on geotagged social media data mining

Abdul Majid, Ling Chen, Gencai Chen, Hamid Turab Mirza, Ibrar Hussain, John Woodward
2013 International Journal of Geographical Information Science  
These results indicate that collaborative filtering method is effective in recommending places in the case of main tourist tours, whereas it has problems in the case of very short and targeted visit.  ...  textual tags and enrich with supplementary information provided from a Web service (i.e., Google Places) to give semantic meaning to aggregated locations.  ... 
doi:10.1080/13658816.2012.696649 fatcat:4zo5tk4tibc5xlqsnugqsefjva

Tweet-SCAN: An event discovery technique for geo-located tweets

Joan Capdevila, Jesús Cerquides, Jordi Nin, Jordi Torres
2017 Pattern Recognition Letters  
The proposed technique models textual content through a probabilistic topic model called Hierarchical Dirichlet Process and introduces Jensen-Shannon distance for the task of neighborhood identification  ...  As a matter of fact, we show Tweet-SCAN performance in two real data sets of geo-located tweets posted during Barcelona local festivities in 2014 and 2015, for which some of the events were identified  ...  -00067), by the SGR programme (2014-SGR-1051) of the Catalan Government and by COR (TIN2012-38876-C02-01) project.  ... 
doi:10.1016/j.patrec.2016.08.010 fatcat:gtcv2a4kxve7ngae62fmuoe44i

Making sense of social media streams through semantics: A survey

Kalina Bontcheva, Dominic Rout
2014 Semantic Web Journal  
This paper defines five key research questions in this new application area, examined through a survey of state-of-the-art approaches for mining semantics from social media streams; user, network, and  ...  Using semantic technologies for mining and intelligent information access to social media is a challenging, emerging research area.  ...  The authors wish to thank Marta Sabou and Arno Scharl for the discussions on crowdsourcing and its role in semantic technologies research, as well as Diana Maynard for the discussions on opinion mining  ... 
doi:10.3233/sw-130110 fatcat:uytdbegs3ngcbpu62i4trrxjni

Choosing the content of textual summaries of large time-series data sets

2006 Natural Language Engineering  
In this paper we develop an architecture for generating short (a few sentences) summaries of large (100KB or more) time-series data sets.  ...  We also describe and evaluate SumTime-Turbine, a prototype system which uses this architecture to generate textual summaries of sensor data from gas turbines.  ...  Rob Milne and Mr. Jon Aylett, for their contributions to knowledge acquisition and assessment of the prototype system. This project is supported by the UK EPSRC under grant  ... 
doi:10.1017/s1351324905004031 fatcat:dzx3fwenrfbapcu4looeciq6he

A Geolocation Analytics-Driven Ontology for Short-Term Leases: Inferring Current Sharing Economy Trends

Georgios Alexandridis, Yorghos Voutos, Phivos Mylonas, George Caridakis
2020 Algorithms  
A rather solid case-study, based on the aforementioned type of data regarding Athens, Greece, is addressed in detail, studying the different degrees of expansion & prevalence of the phenomenon among the  ...  Short-term property rentals are perhaps one of the most common traits of present day shared economy.  ...  and various points of interest (POIs) such as shops, restaurants, bars and historical landmarks, both in the direct vicinity of their temporary residence and afar in the city.  ... 
doi:10.3390/a13030059 fatcat:c2cibk5m6fbpjia5tklcfhb3de

Boosting image retrieval through aggregating search results based on visual annotations

Ximena Olivares, Massimiliano Ciaramita, Roelof van Zwol
2008 Proceeding of the 16th ACM international conference on Multimedia - MM '08  
When using a textual filter on the search space in combination with the aggregated approach an additional boost in retrieval performance is observed, which underlines the need for large scale content-based  ...  Online photo sharing systems, such as Flickr and Picasa, provide a valuable source of human-annotated photos.  ...  It is difficult for a user to express the visual characteristics of the desired image only using textual clues.  ... 
doi:10.1145/1459359.1459386 dblp:conf/mm/OlivaresCZ08 fatcat:5ehhsdbdlbfwvaq4bn6z3ruzqm

Linked Open Data in Location-Based Recommendation System on Tourism Domain: a survey

Phatpicha Yochum, Liang Chang, Tianlong Gu, Manli Zhu
2020 IEEE Access  
This work aims not only to present a systematic review and mapping of the linked open data in location-based recommendation system on tourism domain, but also to provide an overview of the current research  ...  for reacting to the needs of tourists.  ...  [16] studied tourist trip problems by comprising different point of interests with a reasonable routing for a short city trip.  ... 
doi:10.1109/access.2020.2967120 fatcat:yqwkrko6mzfw5e5kckfaxbxzju

Modeling Analogies for Human-Centered Information Systems [chapter]

Christoph Lofi, Christian Nieke
2013 Lecture Notes in Computer Science  
Analogies are considered to be one of the core concepts of human cognition and communication, and are very efficient at conveying complex information in a natural fashion.  ...  Integrating analogies into modern information systems paves the way for future truly human-centered paradigms for interacting with data and information, and opens up a number of interesting scientific  ...  This simple analogy communicates a lot of implicit information, as for example that the Skytree is an iconic landmark of Tokyo, and a great vantage point.  ... 
doi:10.1007/978-3-319-03260-3_1 fatcat:wouwvhd72nhdhne6bbrczbl6hy

Context-aware Image Tweet Modelling and Recommendation

Tao Chen, Xiangnan He, Min-Yen Kan
2016 Proceedings of the 2016 ACM on Multimedia Conference - MM '16  
part of user interest modelling.  ...  Finally, to spur future studies, we have released both the code of our recommendation model and our image tweet dataset.  ...  We also would like to thank Yongfeng Zhang and Hanwang Zhang for their help and discussions.  ... 
doi:10.1145/2964284.2964291 dblp:conf/mm/ChenHK16 fatcat:nepnjdu5vbffbhrhkisac5p5fe

Recent Trends in Deep Learning Based Open-Domain Textual Question Answering Systems

Zhen Huang, Shiyi Xu, Minghao Hu, Xinyi Wang, Jinyan Qiu, Yongquan Fu, Yuncai Zhao, Yuxing Peng, Changjian Wang
2020 IEEE Access  
To address this issue, we present a thorough survey to explicitly give the task scope of open-domain textual QA, overview recent key advancements on deep learning based open-domain textual QA, illustrate  ...  However, a comprehensive review of existing approaches and recent trends is lacked in this field.  ...  [72] studied several representation learning models and found that attentive LSTM can be very effective on the Pairwise mode training.  ... 
doi:10.1109/access.2020.2988903 fatcat:po4euxfronf3pob52qc2wcgrre
« Previous Showing results 1 — 15 out of 1,429 results