Abstract

Abstract
Large language models (LLMs) have substantially pushed artificial intelligence (AI) research and applications in the last few years. They are currently able to achieve high effectiveness in different natural language processing (NLP) tasks, such as machine translation, named entity recognition, text classification, question answering, or text summarization. Recently, significant attention has been drawn to OpenAI's GPT models' capabilities and extremely accessible interface. LLMs are nowadays routinely used and studied for downstream tasks and specific applications with great success, pushing forward the state of the art in almost all of them. However, they also exhibit impressive inference capabilities when used off the shelf without further training. In this paper, we aim to study the behavior of pre-trained language models (PLMs) in some inference tasks they were not initially trained for. Therefore, we focus our attention on very recent research works related to the inference capabilities of PLMs in some selected tasks such as factual probing and common-sense reasoning. We highlight relevant achievements made by these models, as well as some of their current limitations that open opportunities for further research.This article is categorized under:Fundamental Concepts of Data and Knowledge > Key Design Issues in DataMiningTechnologies > Artificial Intelligence

Abstract
The first edition of the Implicit Author Characterization from Texts for Search and Retrieval (IACT'23) aims at bringing to the forefront the challenges involved in identifying and extracting from texts implicit information about authors (e.g., human or AI) and using it in IR tasks. The IACT workshop provides a common forum to consolidate multi-disciplinary efforts and foster discussions to identify the wide-ranging issues related to the task of extracting implicit author-related information from the textual content, including novel tasks and datasets. We will also discuss the ethical implications of implicit information extraction. In addition, we announce a shared task focused on automatically determining the literary epochs of written books.

Abstract
The first's library projects occur some years ago with digitization, but just in 1996, the first's web archive initiatives start occurring. Such, was based in the Internet growth and in its increasing use, items that revealed to be an opportunity to transform and readapt the traditional library services. In this context, search engines play a fundamental role of support to the new paradigm of knowledge, by capturing, storing and providing access to the resources, allowing the existence of a digital library in each computer with internet access. In this article we analyze the ways of developing a digital library, taking higher attention to the web harvesting technique, and presenting digital libraries capabilities and limitations. Then we fully summarize relevant projects and initiatives, to finally study the role of search engines in what concerns to, digital preservation, access and information diffusion.

Abstract
Temporal Web Image Retrieval can be defined as the process that retrieves sets of Web images with their temporal dimension from explicit or implicit temporal text queries. Supposing that (a) the temporal dimension is included in image indexing and (b) the query is explicitly expressed with a time tag (e. g. "Fukushima 2011"), the retrieval task can be straightforward as image retrieval has been studied for several years with success. However, text queries are usually implicit in time (e. g. "Second World War") and automatically capturing the time dimension included in Web images is a challenge that has not been studied so far to the best of our knowledge. In this paper, we will discuss different research issues about Temporal Web Image Retrieval and the current progresses of our research in temporal ephemeral clustering and temporal image filtering.

Abstract
After a continuously development in on-line availability, most of the countries are close to reach the highest point of public services maturity. The future of e-Gov should now go through accessibility questions and m-Gov, providing a new set of user-centred services, personalized and based on alerts that could be programmed taking into account knowledge based in the localization of the user. In this article we will analyze the stage of e-Gov in Europe based in a report of the European Commission, which allows, the realization of a comparative analysis of the evolution occurred between 2004 and 2006 in the 28 countries part of the study. Following, we analyze the case of Portugal, pointing out some of the reasons to the success of the measures applied. Finally we project the future of e-Gov in terms of accessibility questions, platform access independence and user-centred services.