Abstract
Over the past fewdecades, the amount of information generated turned the Web into the largest knowledge infrastructure existing to date. Web archives have been at the forefront of data preservation, preventing the losses of significant data to humankind. Different snapshots of the web are saved everyday enabling users to surf the past web and to travel through this overtime. Despite these efforts, many people are not aware that the web is being preserved, often finding these infrastructures to be unattractive or difficult to use, when compared to common search engines. In this paper, we give a step towards making use of this preserved information to develop Public Archive an intuitive interface that enables end-users to search and analyze a large-scale of 67,242 past preserved news articles belonging to a Portuguese reference newspaper (Jornal Publico). The referred collection was obtained by scraping 10,976 versions of the homepage of the Jornal Publico preserved by the Portuguese web archive infrastructure (Arquivo.pt) during the time-period of 2010 to 2021. By doing this, we aim, not only to mark a stand in what respects to make use of this preserved information, but also to come up with an easy-to-follow solution, the Public Archive python package, which creates the roots to be used (with minor adaptations) by other news source providers interested in offering their readers access to past news articles.

Abstract
Versioned documents are common in many situations and play a vital part in numerous applications enabling an overview of the revisions made to a document or document collection. However, as documents increase in size, it gets difficult to summarize and comprehend all the changes made to versioned documents. In this paper, we propose a novel research problem of contrastive keyword extraction from versioned documents, and introduce an unsupervised approach that extracts keywords to reflect the key changes made to an earlier document version. In order to provide an easy-to-use comparison and summarization tool, an open-source demonstration is made available which can be found at https://contrastive-keyword-extraction.streamlit.app/.

Abstract
[No abstract available]

Abstract

Abstract

Abstract
This paper describes the participation of the Artificial Intelligence and Information Retrieval (AIIR) Lab from the University of Southern Maine and the Laboratory of Artificial Intelligence and Decision Support (LIAAD) lab from INESC TEC in the CLEF 2023 SimpleText lab. There are three tasks defined for SimpleText: (T1) What is in (or out)?, (T2) What is unclear?, and (T3) Rewrite this!. Five runs were submitted for Task 1 using traditional Information Retrieval, and Sentence-BERT models. For Task 2, three runs were submitted, using YAKE! and KBIR keyword extraction models. Finally, for Task 3, two models were deployed, one using OpenAI Davinci embeddings and the other combining two unsupervised simplification models.