Newsangler

Oppdateringer fra september, 2020 Vis/skjul kommentartråder | Tastatursnarveier

• 

  Andreas Lothe Opdahl 2:19 pm - September 9, 2020 Permalenke | Svar  

  Paper accepted for the Computers in Industry journal 

  Our paper about the previous News Hunter prototype is accepted for publication in Elsevier’s journal Computers in Industry: A Knowledge-Graph Platform for Newsrooms by Arne Berven at Wolftech, along with Ole A. Christensen, Sindre Moldeklev, Andreas L. Opdahl, and Kjetil J. Villanger. It significantly updates, improves, elaborates, and extends our previous NOKOBIT paper from 2018.

  Abstract; Journalism is challenged by digitalisation and social media, resulting in lower subscription numbers and reduced advertising income. Information and communication techniques (ICT) offer new opportunities. Our research group is collaborating with a software developer of news production tools for the international market to explore how social, open, and other data sources can be leveraged for journalistic purposes. We have developed an architecture and prototype called News Hunter that uses knowledge graphs, natural-language processing (NLP), and machine learning (ML) together to support journalists. Our focus is on combining existing data sources and computation and storage techniques into a flexible architecture for news journalism. The paper presents News Hunter along with plans and possibilities for future work.

   

  Svar Avbryt svar

  Obligatoriske felt er merket *

  Navn *

  E-post *

  Nettsted

  Lagre mitt navn, e-post og nettside i denne nettleseren for neste gang jeg kommenterer.

  Δ

• 

  Andreas Lothe Opdahl 1:00 pm - June 15, 2020 Permalenke | Svar  

  New journal paper: Analysis and Design of Computational News Angles 

  A new paper is out on representing and analysing news angles formally: https://ieeexplore.ieee.org/abstract/document/9127417 . It is a collaboration between the University of Bergen and the Open University in Milton Keynes, UK.

  Abstract: A key skill for a journalist is the ability to assess the newsworthiness of an event or situation. To this purpose journalists often rely on news angles, conceptual criteria that are used both i) to assess whether something is newsworthy and also ii) to shape the structure of the resulting news item. As journalism becomes increasingly computer-supported, and more and more sources of potentially newsworthy data become available in real time, it makes sense to try and equip journalistic software tools with operational versions of news angles, so that, when searching this vast data space, these tools can both identify effectively the events most relevant to the target audience, and also link them to appropriate news angles. In this paper we analyse the notion of news angle and, in particular, we i) introduce a formal framework and data schema for representing news angles and related concepts and ii) carry out a preliminary analysis and characterization of a number of commonly used news angles, both in terms of our formal model and also in terms of the computational reasoning capabilities that are needed to apply them effectively to real-world scenarios. This study provides a stepping stone towards our ultimate goal of realizing a solution capable of exploiting a library of news angles to identify potentially newsworthy events in a large journalistic data space.

  Motta, E., Daga, E., Opdahl, A. L., & Tessem, B. (2020). Analysis and Design of Computational News Angles. IEEE Access, 8, 120613-120626.

   
• 

  Andreas Lothe Opdahl 12:48 pm - June 1, 2020 Permalenke | Svar  

  New journal paper: Ontologies for finding journalistic angles 

  A new paper is out in the Software and Systems Modeling (SoSyM) journal: https://link.springer.com/article/10.1007/s10270-020-00801-w . It extends our EMMSAD’2019 paper.

  Abstract: Journalism relies more and more on information and communication technology (ICT). ICT-based journalistic knowledge platforms continuously harvest potentially news-relevant information from the Internet and make it useful for journalists. Because information about the same event is available from different sources and formats vary widely, knowledge graphs are emerging as a preferred technology for integrating, enriching, and preparing information for journalistic use. The paper explores how journalistic knowledge graphs can be augmented with support for news angles, which can help journalists to detect newsworthy events and make them interesting for the intended audience. We argue that finding newsworthy angles on news-related information is an important example of a topical problem in information science: that of detecting interesting events and situations in big data sets and presenting those events and situations in interesting ways.

  Opdahl, A. L., & Tessem, B. (2020). Ontologies for finding journalistic angles. Software and Systems Modeling, 1-17.

   
• 

  Andreas Lothe Opdahl 4:37 pm - April 14, 2020 Permalenke | Svar  

  Tareq Al-Moslmi presents paper at ICACIn’20 

  At the 1st International Conference on Advanced Computing and Informatics, Tareq Al-Moslmi presented his joint paper on blockchains and smart contracts to provide privacy in decentralised data processing.

  Marc Gallofré Ocaña, Abdo Ali Al-Wosabi, and Tareq Al-Moslmi (2020): Towards a Blockchain and Smart Contracts-Based Privacy Framework for Decentralised Data Processing. In Proc. 1st Int. Conf. on Advanced Computing and Informatics, Casablanca, Morocco, April 13-14, 2020.

   
• 

  Andreas Lothe Opdahl 12:58 pm - February 11, 2020 Permalenke | Svar  

  New journal paper: Named Entity Extraction for Knowledge Graphs: A Literature Overview 

  A new paper is out in IEEE Access: https://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=8999622 . It is a comprehensive literature study of approaches that extract, disambiguate and link named entities.

  Abstract: An enormous amount of digital information is expressed as natural-language (NL) text that is not easily processable by computers. Knowledge Graphs (KG) offer a widely used format for representing information in computer-processable form. Natural Language Processing (NLP) is therefore needed for mining (or lifting) knowledge graphs from NL texts. A central part of the problem is to extract the named entities in the text. The paper presents an overview of recent advances in this area, covering: Named Entity Recognition (NER), Named Entity Disambiguation (NED), and Named Entity Linking (NEL).We comment that many approaches to NED and NEL are based on older approaches to NER and need to leverage the outputs of state-of-the-art NER systems. There is also a need for standard methods to evaluate and compare named-entity extraction approaches. We observe that NEL has recently moved from being stepwise and isolated into an integrated process along two dimensions: the first is that previously sequential steps are now being integrated into end-to-end processes, and the second is that entities that were previously analysed in isolation are now being lifted in each other’s context. The current culmination of these trends are the deep-learning approaches that have recently reported promising results.

  Al-Moslmi, T., Ocaña, M. G., Opdahl, A. L., & Veres, C. (2020). Named entity extraction for knowledge graphs: A literature overview. IEEE Access, 8, 32862-32881.

   
• 

  Andreas Lothe Opdahl 8:36 am - December 19, 2019 Permalenke | Svar  

  Bjørnar Tessem presents paper about news angles at AI 2019 in Cambridge 

  On December 17-19, Bjørnar Tessem presented a new paper about analogical reasoning about news angles based on text similarity at the 39th SGAI International Conference on Artificial Intelligence (AI 2019) in Cambridge, UK.

  Tessem, Bjørnar (2019). Analogical New Angles from Text Similarity. In Artificial Intelligence XXXVI, Lecture Notes in Computer Science (LNCS), Springer, pp. 449-455.

   
• 

  Andreas Lothe Opdahl 8:19 am - December 16, 2019 Permalenke | Svar  

  Tareq Al-Moslmi presents papers about named-entity recognition and sentiment analysis at ICOICE 2019 

  Tareq Al-Moslmi presents three papers on named-entity recognition and cross-domain sentiment analysis at the First International Conference of Intelligent Computing and Engineering (ICOICE 2019) in Yemen, one of them co-authored with Marc Gallofré-Ocaña.

  Albared, M., Ocaña, M. G., Ghareb, A., & Al-Moslmi, T. (2019, December). Recent Progress of Named Entity Recognition over the Most Popular Datasets. In 2019 First International Conference of Intelligent Computing and Engineering (ICOICE) (pp. 1-9). IEEE.

  Al-Moslmi, T., Albared, M., Al-Shabi, A., & Abdullah, S. (2019, December). Bidirectional Feature Transfer for Cross-Domain Sentiment Analysis. In 2019 First International Conference of Intelligent Computing and Engineering (ICOICE) (pp. 1-8). IEEE.

  Al-Moslmi, T., Albared, M., Al-Shabi, A., Abdullah, S., & Omar, N. (2019, December). A Comparative Study Of Co-Occurrence Strategies for Building A Cross-Domain Sentiment Thesaurus. In 2019 First International Conference of Intelligent Computing and Engineering (ICOICE) (pp. 1-8). IEEE.

   
• 

  Andreas Lothe Opdahl 4:20 pm - December 2, 2019 Permalenke | Svar  

  Csaba Veres presents paper about learnability and verb semantics at AI 2019 

  At the Australasian Joint Conference on Artificial Intelligence (AI 2019), Csaba Veres presented his joint paper on A Machine Learning Benchmark with Meaning: Learnability and Verb Semantics.

  Abstract: Just over thirty years ago the prospect of modelling human knowledge with parallel distributed processing systems without explicit rules, became a possibility. In the past five years we have seen remarkable progress with artificial neural network (ANN) based systems being able to solve previously difficult problems in many cognitive domains. With a focus on Natural Language Processing (NLP), we argue that the progress is in part illusory because the benchmarks that measure progress have become task oriented, and have lost sight of the goal to model knowledge. Task oriented benchmarks are not informative about the reasons machine learning succeeds, or fails. We propose a new dataset in which the correct answers to entailments and grammaticality judgements depend crucially on specific items of knowledge about verb semantics, and therefore errors on performance can be directly traced to deficiencies in knowledge. If this knowledge is not learnable from the provided input, then it must be provided as an innate prior.

  Veres C., Sandblåst B.H. (2019) A Machine Learning Benchmark with Meaning: Learnability and Verb Semantics. In: Liu J., Bailey J. (eds) AI 2019: Advances in Artificial Intelligence. AI 2019. Lecture Notes in Computer Science, vol 11919. Springer, Cham.

   
• 

  Andreas Lothe Opdahl 4:46 pm - September 4, 2019 Permalenke | Svar  

  Tareq Al-Moslmi attends RANLP 2019 and Deep Learning workshop 

  Tareq Al-Moslmi has attended the conference on Recent Advances in Natural Language Processing (RANLP 2019) in Varna in Bulgaria, including a Summer School on Deep Learning in NLP and several workshops.

   
• 

  Andreas Lothe Opdahl 9:09 am - July 6, 2019 Permalenke | Svar  

  Marc Gallofré Ocaña presents plans for the News Hunter platform at summer school 

  At the 2nd International Semantic Web Research Summer School (ISWS 2019) in Bertinoro, Italy, Marc Gallofré Ocaña presented his progress on a journalistic knowledge platform. Poster title: A reference architecture for Big Data Knowledge Graphs-Based Systems to Support Journalists .