Browsing Data Science Institute (Workshop Papers) by Title
Now showing items 59-78 of 118
-
Neologism: Easy Vocabulary Publishing
(2008)Creating, documenting, publishing and maintaining an RDF Schema vocabulary is a complex, timeconsuming task. This makes vocabulary maintainers reluctant to evolve their creations quickly in response to user feedback; it ... -
Neural machine translation of literary texts from English to Slovene
(Machine Translation Summit 2019, 2019-08-19)Neural Machine Translation has shown promising performance in literary texts. Since literary machine translation has not yet been researched for the English-toSlovene translation direction, this paper aims to fulfill ... -
A Non-traditional Inference Paradigm for Learned Ontologies
(CEUR Workshop proceedings, 2007) -
notitio.us - Semantic Information Discovery, Browsing and Sharing
(2007)Searching for information on the Internet became much easier when Google started delivering their service. We got used to getting the most important (probably) results on the top of the list. But more and more ... -
NUIG at the FinSBD Task: Sentence boundary detection for noisy financial PDFs in English and French
(NUI Galway, 2019-08-12)Portable Document Format (PDF) has become the industry-standard document as it is independent of the software, hardware or operating system. Publicly listed companies annually publish a variety of reports and too take ... -
NUIG at TIAD: Combining unsupervised NLP and graph metrics for translation inference
(European Language Resources Association (ELRA), 2020-05-11)In this paper, we present the NUIG system at the TIAD shard task. This system includes graph-based metrics calculated using novel algorithms, with an unsupervised document embedding tool called ONETA and an unsupervised ... -
NUIG-DSI at the WebNLG+ challenge: Leveraging transfer learning for RDF-to-text generation
(Association for Computational Linguistics, 2020-12-18)This paper describes the system submitted by NUIG-DSI to the WebNLG+ challenge 2020 in the RDF-to-text generation task for the English language. For this challenge, we leverage transfer learning by adopting the T5 model ... -
NUIG-DSI’s submission to the GEM Benchmark 2021
(Association for Computational Linguistics, 2021-08-05)This paper describes the submission by NUIG-DSI to the GEM benchmark 2021. We participate in the modeling shared task where we submit outputs on four datasets for data-to-text generation, namely, DART, WebNLG (en), E2E and ... -
On lexicographical networks
(NUI Galway, 2018-12-06)In this study, we analyze various aspects of lexicographical networks. We would like to answer our research questions of what are the characteristics of the lexicographical networks? In addition to the existing notions of ... -
Open social data crime analytics
(IJCAI 17 Melbourne, 2017-07-20)Crime is under-reported. Reporting crime requires the victim to complete a number of administrative obligations. These obligations, as well as the nature of the crime, may create an inertia that discourages the reporting ... -
Passive diagnosis incorporating the PHQ-4 for depression and anxiety
(NUI Galway, 2019)Depression and anxiety are the two most prevalent mental health disorders worldwide, impacting the lives of millions of people each year. In this work, we develop and evaluate a multilabel, multidimensional deep neural ... -
Performing Object Consolidation on the Semantic Web Data Graph
(2007)An important aspect of Semantic Web technologies is the issue of identity and uniquely identifying resources, which is essential for integrating data across sources. Currently, there is poor agreement on the use of ... -
Personalized Question Answering: A Use Case for Business Analysis
(2006)In this paper, we introduce the Personalized Question Answering framework, which aims at addressing certain limitations of existing domain specific Question Answering systems. Current development efforts are ongoing to ... -
Podcast Pinpointer: A Multimedia Semantic Web Application
(IEEE, 2005)In late 2004, a new method of publishing multimedia broadcasts on the Internet became popular called `Podcasting¿. Podcasting incorporates existing feed description formats, namely RSS 2.0, to ... -
Processing ontology alignments with SPARQL
(IEEE, 2008)Solving problems raised by heterogeneous ontologies can be achieved by matching the ontologies and processing the resulting alignments. This is typical of data mediation in which the data must be translated from one ... -
Processing ontology alignments with SPARQL
(IEEE Computer Society, 2008) -
ReConRank: A Scalable Ranking Method for Semantic Web Data with Context
(2006)We present an approach that adapts the well-known PageRank/HITS algorithms to Semantic Web data. Our method combines ranks from the RDF graph with ranks from the context graph, i.e. data sources and their linkage. We present ... -
Relaxing the Basic KR&R Principles to Meet the Emergent Semantic Web
(CEUR-WS, 2008)The paper argues for an alternative, empirical (instead of analytical) approach to a Semantic Web-ready KR&R, motivated by the so far largely untackled need for a feasible emergent content processing. -
The role of negative results for choosing an evaluation approach - a recommender systems case study
(CEUR Workshop Proceedings, 2015-06-01)We describe a case study, which shows how important negative results are in uncovering biased evaluation methodologies. Our re- search question is how to compare a recommender algorithm that uses an RDF graph to a ...