Luís Filipe Cunha

Abstract
The capabilities of the most recent language models have increased the interest in integrating them into real-world applications. However, the fact that these models generate plausible, yet incorrect text poses a constraint when considering their use in several domains. Healthcare is a prime example of a domain where text-generative trustworthiness is a hard requirement to safeguard patient well-being. In this paper, we present Physio, a chat-based application for physical rehabilitation. Physio is capable of making an initial diagnosis while citing reliable health sources to support the information provided. Furthermore, drawing upon external knowledge databases, Physio can recommend rehabilitation exercises and over-the-counter medication for symptom relief. By combining these features, Physio can leverage the power of generative models for language processing while also conditioning its response on dependable and verifiable sources. A live demo of Physio is available at https://physio.inesctec.pt.

Abstract
Event extraction is an NLP task that commonly involves identifying the central word (trigger) for an event and its associated arguments in text. ACE-2005 is widely recognised as the standard corpus in this field. While other corpora, like PropBank, primarily focus on annotating predicate-argument structure, ACE-2005 provides comprehensive information about the overall event structure and semantics. However, its limited language coverage restricts its usability. This paper introduces ACE-2005-PT, a corpus created by translating ACE-2005 into Portuguese, with European and Brazilian variants. To speed up the process of obtaining ACE-2005-PT, we rely on automatic translators. This, however, poses some challenges related to automatically identifying the correct alignments between multi-word annotations in the original text and in the corresponding translated sentence. To achieve this, we developed an alignment pipeline that incorporates several alignment techniques: lemmatization, fuzzy matching, synonym matching, multiple translations and a BERT-based word aligner. To measure the alignment effectiveness, a subset of annotations from the ACE-2005-PT corpus was manually aligned by a linguist expert. This subset was then compared against our pipeline results which achieved exact and relaxed match scores of 70.55% and 87.55% respectively. As a result, we successfully generated a Portuguese version of the ACE-2005 corpus, which has been accepted for publication by LDC.

Abstract
One of the fundamental tasks in Information Extraction (IE) is Event Extraction (EE), an extensively studied and challenging task [13,15], which aims to identify and classify events from the text. This involves identifying the event's central word (trigger) and its participants (arguments) [1]. These elements capture the event semantics and structure, which have applications in various fields, including biomedical texts [42], cybersecurity [24], economics [12], literature [32], and history [33]. Structured knowledge derived from EE can also benefit other downstream tasks such as Question Answering [20,30], Natural Language Understanding [21], Knowledge Base Graphs [3,37], summarization [8,10,41] and recommendation systems [9,18]. Despite the existence of several English EE systems [2,22,25,26], they face limited portability to other languages [4] and most of them are designed for closed domains, posing difficulties in generalising. Furthermore, most current EE systems restrict their scope to the sentence level, assuming that all arguments are contained within the same sentence as their corresponding trigger. However, real-world scenarios often involve event arguments spanning multiple sentences, highlighting the need for document-level EE.

Abstract
The amount of information preserved in Portuguese archives has increased over the years. These documents represent a national heritage of high importance, as they portray the country's history. Currently, most Portuguese archives have made their finding aids available to the public in digital format, however, these data do not have any annotation, so it is not always easy to analyze their content. In this work, Named Entity Recognition solutions were created that allow the identification and classification of several named entities from the archival finding aids. These named entities translate into crucial information about their context and, with high confidence results, they can be used for several purposes, for example, the creation of smart browsing tools by using entity linking and record linking techniques. In order to achieve high result scores, we annotated several corpora to train our own Machine Learning algorithms in this context domain. We also used different architectures, such as CNNs, LSTMs, and Maximum Entropy models. Finally, all the created datasets and ML models were made available to the public with a developed web platform, NER@DI.

Abstract
Currently, there is a vast amount of archival finding aids in Portuguese archives, however, these documents lack structure (are not annotated) making them hard to process and work with. In this way, we intend to extract and classify entities of interest, like geographical locations, people's names, dates, etc. For this, we will use an architecture that has been revolutionizing several NLP tasks, Transformers, presenting several models in order to achieve high results. It is also intended to understand what will be the degree of improvement that this new mechanism will present in comparison with previous architectures. Can Transformer-based models replace the LSTMs in NER? We intend to answer this question along this paper.