Related papers: Knowledge driven Offline to Online Script Conversi…
We present an investigation regarding the challenges faced by student teams across four consecutive iterations of a team-focused, project-based course in software engineering. The studied period includes the switch to fully online…
Signatures are primarily used as a mark of authenticity, to demonstrate that the sender of a message is who they claim to be. In the current digital age, signatures underpin trust in the vast majority of information that we exchange,…
Detecting non-factual content is a longstanding goal to increase the trustworthiness of large language models (LLMs) generations. Current factuality probes, trained using humanannotated labels, exhibit limited transferability to…
Nowadays, the Internet is indispensable when it comes to information dissemination. People rely on the Internet to inform themselves on current news events, as well as to verify facts. We, as a community, are quickly approaching an…
The theory of sampling and recovery of bandlimited graph signals has been extensively studied. However, in many cases, the observation of a signal is quite coarse. For example, users only provide simple comments such as "like" or "dislike"…
Semi-structured content in HTML tables, lists, and infoboxes accounts for a substantial share of factual data on the web, yet the formatting complicates usage, and reliably extracting structured information from them remains challenging.…
We report upon the results of a research and prototype building project \emph{Worldly~OCR} dedicated to developing new, more accurate image-to-text conversion software for several languages and writing systems. These include the cursive…
The machine learning formulation of online learning is incomplete from a systems theoretic perspective. Typically, machine learning research emphasizes domains and tasks, and a problem solving worldview. It focuses on algorithm parameters,…
Biometrics systems have been used in a wide range of applications and have improved people authentication. Signature verification is one of the most common biometric methods with techniques that employ various specifications of a signature.…
Information on cyber-related crimes, incidents, and conflicts is abundantly available in numerous open online sources. However, processing the large volumes and streams of data is a challenging task for the analysts and experts, and entails…
Digital archiving is becoming widespread owing to its effectiveness in protecting valuable books and providing knowledge to many people electronically. In this paper, we propose a novel approach to leverage digital archives for machine…
Real-time video applications require accurate bandwidth estimation (BWE) to maintain user experience across varying network conditions. However, increasing network heterogeneity challenges general-purpose BWE algorithms, necessitating…
Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called knowledge base. Most published work on lifelong learning…
This paper proposes OCR++, an open-source framework designed for a variety of information extraction tasks from scholarly articles including metadata (title, author names, affiliation and e-mail), structure (section headings and body text,…
Conventional reinforcement learning (RL) needs an environment to collect fresh data, which is impractical when online interactions are costly. Offline RL provides an alternative solution by directly learning from the previously collected…
The hit of the COVID-19 pandemic has hugely affected higher education in the world, and as a result, most of the physical classes have been (partially) replaced by online teaching platforms. This transition is challenging even for…
Offline reinforcement learning (RL) allows for the training of competent agents from offline datasets without any interaction with the environment. Online finetuning of such offline models can further improve performance. But how should we…
Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…
The goal in offline data-driven decision-making is synthesize decisions that optimize a black-box utility function, using a previously-collected static dataset, with no active interaction. These problems appear in many forms: offline…
Extracting the relevant information out of a large number of documents is a challenging and tedious task. The quality of results generated by the traditionally available full-text search engine and text-based image retrieval systems is not…