2023
Autores
Lopo, RX; Jorge, AM; Pedroto, M;
Publicação
MACHINE LEARNING AND PRINCIPLES AND PRACTICE OF KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT I
Abstract
Transthyretin-associated Familial Amyloid Polyneuropathy (TTR-FAP) is a chronic fatal disease with a high incidence in Portugal. It is therefore relevant to provide professionals and citizens with a tool that enables a detailed geographical and territorial study. For this reason, we have developed an web based application that brings together techniques applied to spatial data that allow the study of the historical progression and growth of cases in patients' residential areas and areas of origin as well as an epidemic forecast. The tool enables the exploration of geographical longitudinal data at national, district and county levels. High density regions and periods can be visually identified according to parameters selected by the user. The visual evaluation of the data and its comparison across different time spans of the disease era can have an impact on more informed decision making by those working with patients to improve their quality of life, treatment or follow-up. The tool is available online for data exploration and its code is available on GitHub for adaptation to other geospatial scenarios.
2023
Autores
Goncalves, F; Campos, R; Jorge, A;
Publicação
ADVANCES IN INFORMATION RETRIEVAL, ECIR 2023, PT III
Abstract
In recent years, the amount of information generated, consumed and stored has grown at an astonishing rate, making it difficult for those seeking information to extract knowledge in good time. This has become even more important, as the average reader is not as willing to spare more time out of their already busy schedule as in the past, thus prioritizing news in a summarized format, which are faster to digest. On top of that, people tend to increasingly rely on strong visual components to help them understand the focal point of news articles in a less tiresome manner. This growing demand, focused on exploring information through visual aspects, urges the need for the emergence of alternative approaches concerned with text understanding and narrative exploration. This motivated us to propose Text2Storyline, a platform for generating and exploring enriched storylines from an input text, a URL or a user query. The latter is to be issued on the PortugueseWebArchive (Arquivo.pt), therefore giving users the chance to expand their knowledge and build up on information collected from web sources of the past. To fulfill this objective, we propose a system that makes use of the TimeMatters algorithm to filter out non-relevant dates and organize relevant content by means of different displays: `Annotated Text', `Entities', `Storyline', `Temporal Clustering' and `Word Cloud'. To extend the users' knowledge, we rely on entity linking to connect persons, events, locations and concepts found in the text to Wikipedia pages, a process also known as Wikification. Each of the entities is then illustrated by means of an image collected from the Arquivo.pt.
2023
Autores
Silvano, P; Amorim, E; Leal, A; Cantante, I; Silva, F; Jorge, A; Campos, R; Nunes, S;
Publicação
Proceedings of Text2Story - Sixth Workshop on Narrative Extraction From Texts held in conjunction with the 45th European Conference on Information Retrieval (ECIR 2023), Dublin, Ireland, April 2, 2023.
Abstract
News articles typically include reporting events to inform on what happened. These reporting events are not part of the story being told but are nonetheless a relevant part of the news and can pose a challenge to the computational processing of news narratives. They compose a reporting narrative, which is the present study's focus. This paper aims to demonstrate through selected use cases how a comprehensive annotation scheme with suitable tags and links can properly represent the reporting events and the way they relate to the events that make the story. In addition, we put forward a proposal for their visual representation that enables a systematic and detailed analysis of the importance of reporting events in the news structure. Finally, we describe some lexico-grammatical features of reporting events, which can contribute to their automatic detection. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
2023
Autores
Campos, R; Jorge, AM; Jatowt, A; Bhatia, S; Litvak, M;
Publicação
Text2Story@ECIR
Abstract
2023
Autores
Campos, R; Jatowt, A; Jorge, A;
Publicação
Information for a Better World: Normality, Virtuality, Physicality, Inclusivity - 18th International Conference, iConference 2023, Virtual Event, March 13-17, 2023, Proceedings, Part I
Abstract
Extracting keywords from textual data is a crucial step for text analysis. One such process may involve a considerable amount of time when done manually. In this paper, we show how keyword extraction techniques can be used to untap texts of political nature. To accomplish this objective, we conduct a case-study on top of 16 Portuguese (PT) political party programs made available in the context of the legislative elections that took place in 30th of January 2022. Our contributions are two-fold. At the level of resources, we make available a curated dataset and a python notebook that systematizes the process of transforming text into quantitative data and into visual aspects. At the methodological level, we propose to extend the keyword extraction algorithm used in this study to extract the most relevant keywords, not only from individual political party programs, but also across the entire collection of documents. A further contribution is the case-study itself, which calls attention to the fact that such solutions may be of interest not only to common people, but also to journalists or politicians alike. Broadly, we demonstrate how the discussion and the analysis that stems from the results obtained may foster the political science research by making available large-scale processing of documents with marginal costs. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.
2023
Autores
Campos, R; Jorge, A; Jatowt, A; Bhatia, S; Litvak, M;
Publicação
ADVANCES IN INFORMATION RETRIEVAL, ECIR 2023, PT III
Abstract
Over these past five years, significant breakthroughs, led by Transformers and large language models, have been made in understanding natural language text. However, the ability to capture contextual nuances in longer texts is still an elusive goal, let alone the understanding of consistent fine-grained narrative structures in text. These unsolved challenges and the interest in the community are at the basis of the sixth edition of Text2Story workshop to be held in Dublin on April 2nd, 2023 in conjunction with the 45th European Conference on Information Retrieval (ECIR'23). In its sixth edition, we aim to bring to the forefront the challenges involved in understanding the structure of narratives and in incorporating their representation in well-established models, as well as in modern architectures (e.g., transformers) which are now common and form the backbone of almost every IR and NLP application. It is hoped that the workshop will provide a common forum to consolidate the multi-disciplinary efforts and foster discussions to identify the wide-ranging issues related to the narrative extraction and generation task. Text2Story includes sessions devoted to full research papers, work-in-progress, demos and dissemination papers, keynote talks and space for an informal discussion of the methods, of the challenges and of the future of this research area.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.