Abstract
Textual health records of cancer patients are usually protracted and highly unstructured, making it very time-consuming for health professionals to get a complete overview of the patient's therapeutic course. As such limitations can lead to suboptimal and/or inefficient treatment procedures, healthcare providers would greatly benefit from a system that effectively summarizes the information of those records. With the advent of deep neural models, this objective has been partially attained for English clinical texts, however, the research community still lacks an effective solution for languages with limited resources. In this paper, we present the approach we developed to extract procedures, drugs, and diseases from oncology health records written in European Portuguese. This project was conducted in collaboration with the Portuguese Institute for Oncology which, besides holding over 10 years of duly protected medical records, also provided oncologist expertise throughout the development of the project. Since there is no annotated corpus for biomedical entity extraction in Portuguese, we also present the strategy we followed in annotating the corpus for the development of the models. The final models, which combined a neural architecture with entity linking, achieved..1 scores of 88.6, 95.0, and 55.8 per cent in the mention extraction of procedures, drugs, and diseases, respectively.

Abstract
Temporal information extraction (TIE) has attracted a great deal of interest over the last two decades. Such endeavors have led to the development of a significant number of datasets. Despite its benefits, having access to a large volume of corpora makes it difficult to benchmark TIE systems. On the one hand, different datasets have different annotation schemes, which hinders the comparison between competitors across different corpora. On the other hand, the fact that each corpus is disseminated in a different format requires a considerable engineering effort for a researcher/practitioner to develop parsers for all of them. These constraints force researchers to select a limited amount of datasets to evaluate their systems which consequently limits the comparability of the systems. Yet another obstacle to the comparability of TIE systems is the evaluation metric employed. While most research works adopt traditional metrics such as precision, recall, and..1, a few others prefer temporal awareness - a metric tailored to be more comprehensive on the evaluation of temporal systems. Although the reason for the absence of temporal awareness in the evaluation of most systems is not clear, one of the factors that certainly weighs on this decision is the need to implement the temporal closure algorithm, which is neither straightforward to implement nor easily available. All in all, these problems have limited the fair comparison between approaches and consequently, the development of TIE systems. To mitigate these problems, we have developed tieval, a Python library that provides a concise interface for importing different corpora and is equipped with domain-specific operations that facilitate system evaluation. In this paper, we present the first public release of tieval and highlight its most relevant features. The library is available as open source, under MIT License, at PyPI1 and GitHub(2).

Abstract
Narratives are present in many forms of human expression and can be understood as a fundamental way of communication between people. Computational understanding of the underlying story of a narrative, however, may be a rather complex task for both linguists and computational linguistics. Such task can be approached using natural language processing techniques to automatically extract narratives from texts. In this paper, we present an in depth survey of narrative extraction from text, providing a establishing a basis/framework for the study roadmap to the study of this area as a whole as a means to consolidate a view on this line of research. We aim to fulfill the current gap by identifying important research efforts at the crossroad between linguists and computer scientists. In particular, we highlight the importance and complexity of the annotation process, as a crucial step for the training stage. Next, we detail methods and approaches regarding the identification and extraction of narrative components, their linkage and understanding of likely inherent relationships, before detailing formal narrative representation structures as an intermediate step for visualization and data exploration purposes. We then move into the narrative evaluation task aspects, and conclude this survey by highlighting important open issues under the domain of narratives extraction from texts that are yet to be explored.

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
Deep learning approaches have become popular in sentiment analysis because of their competitive performance. The downside of this approach is that they do not provide understandable explanations on how the sentiment values are calculated. Previous approaches that used sentiment lexicons for sentiment analysis can do that, but their performance is lower than deep learning approaches. Therefore, it is natural to wonder if the two approaches can be combined to exploit their advantages. In this chapter, we present a neuro-symbolic approach that combines both symbolic and deep learning approaches for sentiment analysis tasks. The symbolic approach exploits sentiment lexicon and shifter patterns-which cover the operations of inversion/reversal, intensification, and attenuation/downtoning. The deep learning approach used a pre-trained language model (PLM) to construct sentiment lexicon. Our experimental result shows that the proposed approach leads to promising results, substantially better than the results of a pure lexicon-based approach. Although the results did not reach the level of the deep learning approach, a great advantage is that sentiment prediction can be accompanied by understandable explanations. For some users, it is very important to see how sentiment is derived, even if performance is a little lower. © 2023 The authors and IOS Press. All rights reserved.

Abstract
Deep learning approaches have become popular in sentiment analysis because of their competitive performance. The downside of this approach is that they do not provide understandable explanations on how the sentiment values are calculated. Previous approaches that used sentiment lexicons for sentiment analysis can do that, but their performance is lower than deep learning approaches. Therefore, it is natural to wonder if the two approaches can be combined to exploit their advantages. In this chapter, we present a neuro-symbolic approach that combines both symbolic and deep learning approaches for sentiment analysis tasks. The symbolic approach exploits sentiment lexicon and shifter patterns-which cover the operations of inversion/reversal, intensification, and attenuation/downtoning. The deep learning approach used a pre-trained language model (PLM) to construct sentiment lexicon. Our experimental result shows that the proposed approach leads to promising results, substantially better than the results of a pure lexicon-based approach. Although the results did not reach the level of the deep learning approach, a great advantage is that sentiment prediction can be accompanied by understandable explanations. For some users, it is very important to see how sentiment is derived, even if performance is a little lower. © 2023 The authors and IOS Press. All rights reserved.