Outputs (52)

Reproducing "Show, attend and tell: Neural image caption generation with visual attention" (2023)
Presentation / Conference Contribution

This paper replicates the experiment presented in the work of Xu et al. [1], and
examines errors in the generated captions. The analysis of the identified errors aims to provide
deeper insight into the underlying causes. This study also encompass... Read More about Reproducing "Show, attend and tell: Neural image caption generation with visual attention".

Towards idea mining: Problem-solution phrases extraction from text (2022)
Presentation / Conference Contribution

This paper investigates the feasibility of problem-solution
phrases extraction from scientific publications using neural network approaches. Bidirectional Long Short-Term Memory with Conditional Random Fields (Bi-LSTM-CRFs) and Bidirectional Encoder... Read More about Towards idea mining: Problem-solution phrases extraction from text.

Towards idea mining: Problem-solution phrase extraction from text (2022)
Presentation / Conference Contribution

This paper investigates the feasibility of problem-solution phrases extraction from scientific publications using neural network approaches. Bidirectional Long Short-Term Memory with Conditional Random Fields (Bi-LSTM-CRFs) and Bidirectional Encoder... Read More about Towards idea mining: Problem-solution phrase extraction from text.

Enhancing reflective learning experiences in museums through interactive installations (2018)
Journal Article

In this study we examine the effect that several technological affordances have upon the experiences of children while visiting a museum, focusing upon engagement, discussion and reflection. The museum is the Baba Nyonya Heritage Museum in Malacca, M... Read More about Enhancing reflective learning experiences in museums through interactive installations.

Towards computation of novel ideas from corpora of scientific text (2015)
Presentation / Conference Contribution

© Springer International Publishing Switzerland 2015. In this work we present a method for the computation of novel ‘ideas’ from corpora of scientific text. The system functions by first detecting concept noun-phrases within the titles and abstracts... Read More about Towards computation of novel ideas from corpora of scientific text.

On the Turing Completeness of the Semantic Web (2014)
Journal Article

© 2014, Springer Science+Business Media New York. The evidenced fact that “Linking is as powerful as computing” in a dynamic web context has lead to evaluating Turing completeness for hypertext systems based on their linking model. The same evaluatio... Read More about On the Turing Completeness of the Semantic Web.

The ethical and social implications of personalization technologies for e-learning (2014)
Journal Article

Personalization in information systems can be considered beneficial but also ethically and socially harmful. Like many other technologies, the uptake of personalization has been rapid, with inadequate consideration given to its effects. Personalizati... Read More about The ethical and social implications of personalization technologies for e-learning.

Translation techniques in cross-language information retrieval (2012)
Journal Article

Cross-language information retrieval (CLIR) is an active sub-domain of information retrieval (IR). Like IR, CLIR is centered on the search for documents and for information contained within those documents. Unlike IR, CLIR must reconcile queries and... Read More about Translation techniques in cross-language information retrieval.

HCI and the Web (2012)
Book Chapter

Web browsers have no inherent way of presenting the structure and interrelationships of data of any sort. For example, there is no way to visualize even the simple interrelationships of web documents, such as “Where can I go from here?” or “Which doc... Read More about HCI and the Web.

Generating unambiguous URL clusters from web search (2009)
Presentation / Conference Contribution

This paper reports on the generation of unambiguous clusters of from clickthrough data from the MSN search query log (the RFP 2006 dataset). Selections (clickthroughs) by a user from a single query can be assumed to have some semantic relevance, and... Read More about Generating unambiguous URL clusters from web search.