Knowledge sharing in manufacturing using LLM-powered tools: User study and model benchmarking

Recent advances in natural language processing enable more intelligent ways to support knowledge sharing in factories. In manufacturing, operating production lines has become increasingly knowledge-intensive, putting strain on a factory's capacity to train and support new operators. This paper introduces a Large Language Model (LLM)-based system...

Extractive Explanations for Interpretable Text Ranking

Neural document ranking models perform impressively well due to superior language understanding gained from pre-Training tasks. However, due to their complexity and large number of parameters these (typically transformer-based) models are often non-interpretable in that ranking decisions can not be clearly attributed to specific parts of the...

Investigating fair rankers under the expected exposure framework

As the amount of information available in the world grows, Information Retrieval (IR) systems have become an integral part of day to day life. They determine what subset of the large pool of information is shown to people. IR algorithms determine which items should be returned in response to a query and rank the results in a ranked list.<br/...

Towards Memorable Information Retrieval

Information overload is a problem many of us can relate to nowadays. The deluge of user generated content on the Internet, and the easy accessibility to a vast amount of data compounds the problem of remembering and retaining information that is consumed. To make information consumed more memorable, strategies such as note-taking have been found...

Geo-Distinctive Visual Element Matching for Location Estimation of Images

We propose an image representation and matching approach that substantially improves visual-based location estimation for images. The main novelty of the approach, called distinctive visual element matching (DVEM), is its use of representations that are specific to the query image whose location is being predicted. These representations are...

Where will you comment next? Exploiting comments for personalized recommendations

Since the advent of Web 2.0, users have not only increasingly created content, but also contributed reactions to content in the form of comments. Comments are challenging to analyze due to their short lengths and informal style, meaning that any individual comment provides very little data to work with and is highly variable. However, comments...

Personalized Microblog Search on Twitter

This thesis describes our approach to microblog search personalization. The approach uti-lizes implicit information about the user’s interests to personalize original search results. We first present how do we model users’ preferences on Twitter. Subsequently, we investi-gate different ways to represent search results so that they can be...

A Domain-Specific Language for Internal Site Search

The importance of search facilities on a website grows with the size of the content being served. User expectations for internal site search are greatly influenced by global web search engines, requiring developers of web applications to go beyond basic search functionality. In this thesis, a domain-specific language (DSL) for internal site...

Querying Sparse Matrices for Information Retrieval

For many years, information retrieval (IR) systems could have been adequately described as applications that assign an estimate of relevancy to a pair of document and query, each represented as a 'bag-of-words'. The implementation of such search systems has been relatively straightforward, and most engineers code retrieval models directly on top...

Vector-Based Semantic Expansion Approach: An Application to Patent Retrieval

Patent collection is increasing incrementally. Most of the new technological information is from patent documents, and retrieving specific patents in such a large pool of documents has become a challenging issue for both patent examiners and normal/inexperienced users. Nowadays, most of the retrieval systems (patent retrieval systems) search for...

Exploiting Twitter to fulfill information needs during incidents

How can Twitter be exploited to fulfill information needs of users on Twitter during incidents? In this Thesis this question wil be investigated and a strategy to locate tweets which fulfill information needs will be introduced. First, techniques are proposed to automatically detect incidents given an unstructured incident data source and...

Personalised Access to Social Media

On many websites users can personally contribute information, ranging from short text messages to photos and videos. Users can see the information contributed by others and respond to it. These social media actively engage their community in the structuring of the collection by making use of collaborative annotation methods. Next to an improved...

An Industrial Case Study in Reconstructing Requirements Views

Preprint of article published in: Empirical Software Engineering (Springer), 13 (6), 2008; doi:10.1007/s10664-008-9078-4 Requirements views, such as coverage and status views, are an important asset for monitoring and managing software development projects. We have developed a method that automates the process of reconstructing these views, and...

Coderivative Document Recognition

Knowledge management in large enterprises currently depends very much on the active participation of the employees. If an employee is unable or unwilling to share his knowledge,the knowledge management fails. To counter this situation, the documents of all employees can be collected automatically and stored in a knowledge management application....

Context Knowledge: Supporting Designers' Information Search in the Early Design Phases

Large amounts of data, information and knowledge are used during a design process. And it is proven from past researches that the absence of context is one of the reasons of the difficulties of utilizing data, information and knowledge in a design. This research work explored the concept of context that has been used in various domains and...

Spatial Orientation in Virtual Environments

Recently, a growing interest can be detected in the application of Virtual Environment (VE) technology as an operator interface. VEs are three-dimensional computer-generated images that can be shown on a conventional monitor, on a large screen display, or on a head-mounted display. In order to use these three-dimensional interfaces for finding...