Blog ← Saatviga Sudhahar

Graph Attention networks GATs) – A non-spectral approach to generalising convolutions to the graph

Jan

1

2021

Recently Graph convolutional networks (GCNs) have gained significant interest in the deep learning world to solve problems with knowledge graphs (KGs) containing nodes, edges and relationships. Training a model to solve a problem with graph data is complex due to its multi-relational nature, types of relations, nodes, attributes and also noise when extracted from textual sources using natural language processing (NLP). Primarily two different kind of problems have been studied ...

Knowledge Graph Embeddings for Entity, Link Prediction – The Basics

Jan

1

2021

Knowledge graphs are being used in the field of machine learning for various applications including question & answering, link prediction, fact checking, entity disambiguation etc. For many of these applications finding the missing relationships in the graph is important to ensure, completeness, correctness and quality. This involves the task of entity prediction and relationship prediction. Basically a knowledge graph is a collection of entities and relationships between them in the form ...

Content Analysis of 150 years of British Periodicals

Jan

15

2017

Previous studies have shown that it is possible to detect macroscopic patterns of cultural change over periods of centuries by analyzing large textual time series, specifically digitized books. This method promises to empower scholars with a quantitative and data-driven tool to study culture and society, but its power has been limited by the use of data from books and simple analytics based essentially on word counts. This study addresses these ...

Gender Representation in Online News

Jan

15

2017

It has long been argued that women are under-represented and marginalised in relation to men in the world’s news media. In this research we analysed over two million articles to find out how gender is represented in online news. The study, which is the largest undertaken to date, found men’s views and voices are represented more in online news than women’s. Modern AI, which is frequently in the news, is ...

Coverage of science in the media 2

Mar

9

2015

The contents of English-language online-news over 5 years have been analyzed to explore the impact of the Fukushima disaster on the media coverage of nuclear power. This big data study, based on millions of news articles, involves the extraction of narrative networks, association networks, and sentiment time series. We gathered over 5 million science articles between 1st May 2008 and 31st December 2013. In order to examine how different science-based issues and events are framed by ...

Modular systems for annotation of news articles 4

Feb

9

2015

This study was part of the CompLACS project and the goal was to develop a platform to test algorithms and concepts, and to inspire new algorithms and concepts, within the domain of composing learning systems. One of the four scenarios identified within this goal was “Annotation of News Articles”. This scenario is centered around building modules for the ‘Articles’ blackboard (collection of news articles) that annotate items with descriptors such as tags and fields, that ...

Big Data analysis of the 2012 US presidential elections

Feb

1

2015

The American presidential elections are among the most interesting campaigns because of the sheer amount of resources deployed and the influence of the United States on global governance. This study presents a large-scale analysis of mass media coverage of the 2012 US presidential elections, combining automatic corpus linguistics methods and network analysis to obtain a network representation of the entire campaign coverage by the news media. Mapping the full extent ...

Approaches to document summarization using semantic graphs

Dec

21

2010

Most of the work involves triplet extraction from documents using various tools and then performing co-reference resolution, anaphora resolution and semantic normalization. Finally the refined triplets are formed into a semantic graph. Later a SVM classifier is trained in order to get only the most relevant triplets for summarization purposes. To do this triplets are assigned a set of attributes like, linguistic attributes: the triplet type – subject, verb or object ...

Constructing semantic graphs from text documents

Oct

13

2010

The rapid development of the World Wide Web and online information services has increased the accessibility of information everywhere. It is necessary to provide information that is more structured and synthesized in order to make things more efficient. Automatic generation of text through information extraction is a key area in linguistic research today. This includes automatic question and answering, document summarization and visualization techniques. Semantic graph is the major source ...