In this paper we demo the Temporal Game, a novel approach to temporal relation extraction that casts the task as an interactive game. Instead of directly annotating interval-level relations, our approach decomposes them into point-wise comparisons between the start and end points of temporal entities. At each step, players classify a single point relation, and the system applies temporal closure to infer additional relations and enforce consistency. This point-based strategy naturally supports both interval and instant entities, enabling more fine-grained and flexible annotation than any previous approach. The Temporal Game also lays the groundwork for training reinforcement learning agents, by treating temporal annotation as a sequential decision-making task. To showcase this potential, the demo presented in this paper includes a Game mode, in which users annotate texts from the TempEval-3 dataset and receive feedback based on a scoring system, and an Annotation mode, that allows custom documents to be annotated and resulting timeline to be exported. Therefore, this demo serves both as a research tool and an annotation interface. The demo is publicly available at https://temporal-game.inesctec.pt, and the source code is open-sourced to foster further research and community-driven development in temporal reasoning and annotation.

Events like Valentine's Day and Christmas can influence user intent when interacting with search engines. For example, a user searching for gift around Valentine's Day is likely to be looking for Valentine's-themed options, whereas the same query close to Christmas would more likely suggest an interest in Holiday-themed gifts. These shifts in user intent, driven by temporal factors, are often implicit but important to determine the relevance of search results. In this demo, we explore how incorporating temporal awareness can enhance search relevance in an e-commerce setting. We constructed a database of 2K events and, using historical purchase data, developed a temporal model that estimates each event's importance on a specific date. The most relevant events on the date the query was issued are then used to enrich search results with event-specific items. Our demo illustrates how this approach enables a search system to better adapt to temporal nuances, ultimately delivering more contextually relevant products.

Temporal expression identification is crucial for understanding texts written in natural language. Although highly effective systems such as HeidelTime exist, their limited runtime performance hampers adoption in large-scale applications and production environments. In this paper, we introduce the TEI2GO models, matching HeidelTime's effectiveness but with significantly improved runtime, supporting six languages, and achieving state-of-the-art results in four of them. To train the TEI2GO models, we used a combination of manually annotated reference corpus and developed ``Professor HeidelTime'', a comprehensive weakly labeled corpus of news texts annotated with HeidelTime. This corpus comprises a total of $138,069$ documents (over six languages) with $1,050,921$ temporal expressions, the largest open-source annotated dataset for temporal expression identification to date. By describing how the models were produced, we aim to encourage the research community to further explore, refine, and extend the set of models to additional languages and domains. Code, annotations, and models are openly available for community exploration and use. The models are conveniently on HuggingFace for seamless integration and application.

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 F1, 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 PyPI and GitHub.

Health consumers usually face difficulties on their online searches, mainly because of the differences between terminologies used by laypeople and health professionals. This work presents a tool, HealthTranslator, available as a Google Chrome extension that intends to reduce this terminological gap while users are searching the Web for health information. HealthTranslator automatically annotates medical concepts in web documents, providing additional information, such as concept definition, related concepts and links to external references. The solution was evaluated regarding its: (a) performance - the document processing is done gradually, typically from the top to the bottom of the document and performance was not an issue raised by the users; (b) concept coverage - the solution was compared to a similar extension performing in English recognizing significantly more concepts. A comparison with a corpus of Portuguese documents manually annotated with medical concepts showed an average F-measure between 27% and 33%, depending on the type of concepts being recognized; (c) users' receptivity to HealthTranslator and its usability - many aspects were surveyed on a user study. In general, the extension has a good acceptance and users find it useful.