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
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.