Alexandria at JCDL 2018

The 2018 ACM/IEEE Joint Conference on Digital Libraries (JCDL 2018) was held in Fort Worth (Texas, USA) on 3-6 June. The Alexandria project was again present in this annual venue with one full research paper. The paper, entitled  “Ranking Archived Documents for Structured Queries on Semantic Layers”, was presented by Dr. Pavlos Fafalios and is co-authored by Prof. Wolfgang Nejdl.

The paper introduces the problem of ranking archived documents for structured queries on semantic layers and proposes two ranking models (a probabilistic one and a Random Walk-based one) which jointly consider: i) the relativeness of a document to the query entities, ii) the timeliness of a document’s publication date, iii) the temporal relatedness of the query entities to other entities mentioned in the documents.

A preprint of the article is available at:

The presentation slides are available at:

ESWC 2018 with Alexandria Contributions

The 15th Extended Semantic Web Conference (ESWC 2018) was held in Heraklion (Crete, Greece) on 3-7 June 2018. The Alexandria project was present with the following publications:

TweetsKB: A Public and Large-Scale RDF Corpus of Annotated Tweets (by Pavlos Fafalios, Vasileios Iosifidis, Eirini Ntoutsi, and Stefan Dietze). Nominated for the “Best Resource Paper” award! [PAPER]
EventKG: A Multilingual Event-Centric Temporal Knowledge Graph (by Simon Gottschalk and Elena Demidova) [PAPER]

In addition, the following papers were presented in ESWC workshops:

Time-Aware and Corpus-Specific Entity Relatedness (by Nilamadhaba Mohapatra, Vasileios Iosifidis, Asif Ekbal, Stefan Dietze, and Pavlos Fafalios) – Workshop on Deep Learning for Knowledge Graphs and Semantic Technologies (DL4KGS) [PAPER]
Heuristics-based Query Reordering for Federated Queries in SPARQL 1.1 and SPARQL-LD (by Pavlos Fafalios and Yannis Tzitzikas) – 2nd Workshop on Querying the Web of Data (QuWeDa) [PAPER]

Alexandria at Web Science 2018

The 10th International ACM Web Science Conference was held from Sunday May 27 to Wednesday May 30 (2018) in Amsterdam, The Netherlands. The Alexandria project was present in this annual venue with the following contributions:
– Viewpoint Discovery and Understanding in Social Networks (by Mainul Quraishi, Pavlos Fafalios, and Eelco Herder) [PAPER]
– DistrustRank: Spotting False News Domains (by Vinicius Woloszyn and Wolfgang Nejdl) [PAPER]

The first paper proposes a graph partitioning method that exploits social interactions to enable the discovery of different communities (representing different viewpoints) discussing about a controversial topic in a social network like Twitter. To explain the discovered viewpoints, the paper describes a method, called Iterative Rank Difference (IRD), which allows detecting descriptive terms that characterize the different viewpoints as well as understanding
how a specific term is related to a viewpoint (by detecting other related descriptive terms). Such a method enables better understanding of ongoing political or societal debates, or analyzing and interpreting the course of historical events retrospectively.

The second paper proposes a semi-supervised learning strategy to automatically separate fake news from reliable news sources. The ouput is a trust (or distrust) rank that can be used in two ways: a) as a counter-bias to be applied when News about a specific subject is ranked (in order to discount possible boosts achieved by false claims), and b) to assist humans to identify sources that are likely to inclde fake news (or that are likely to be reputable), suggesting websites that should be examined more closely or to be avoided.

EMNLP 2017 with Alexandria Contributions

In this year’s Empirical Methods in Natural Language Processing (EMNLP) conference, members of the Alexandria project, Besnik Fetahu, Avishek Anand and Katja Markert, will be presenting their work on determining citation span for references in Wikipedia pages.

EMNLP is one of the top-tier venues for works in the field of Computational Linguistics. The importance of this conference, is shown by the statistics of this year’s conference, which had an increase of about 50% in terms of submissions compared to the last years.

For more explanation and the outcomes of this work we refer to the page providing more details and the ground-truth.

What does the internet know about the development of software?

Software is dynamic, and is subject to continuous development. In fact, the boundaries between different states and versions of a software program in the course of its development are often blurred. It is difficult to grasp the state of a software program; it can only, if at all, be described by its version number. Not only do software programs develop, the way in which they are presented on the internet – whether on the official website or in discussions and descriptions on external websites – is also frequently subject to development. Web archives enable users to track the development of a software program. In the context of the Specialised Information Service Mathematics, a web service was developed (the Tempas TimePortal) that links the temporal development of software websites to the actual software program. In the database for relevant software in mathematics swMATH, the integration of the TimePortal now enables users, on the basis of the website, to track the status of the software program at the time when a scientific article referring to the software was published.

For more details please have look at the full article on the TIB Blog.

Older posts «