BUSCADOR RECOLECTA

The Financial Document Causality Detection Shared Task (FinCausal 2025) aims to improve causality identification in the financial domain through textual data. This shared task focuses on determining causality associated with both events and quantified facts. In this task, a cause can be the justification of a statement or the reason explaining an outcome. Therefore, it is a relation detection task. The main difference compared to the 2023 edition is that the task is framed as a Question Answering (QA) problem. The question is posed in an abstractive manner, while the predicted answer must be extractive. Additionally, the Semantic Answer Similarity (SAS) metric has been introduced.

Participants, given the context and the abstractive question, must extract the literal answer from the context that responds to that question. The questions seek causal-type relationships, either causes or effects.

The task dataset has been extracted from a corpus of Spanish financial annual reports from 2014 to 2018. Participants are provided with a CSV file containing the following fields: ID; Text; Question; Answer.

The standard way to participate is to fine-tune a model using the data annotated by linguists (including Inter-Annotator Agreement, IAA), and then use the fine-tuned model to predict the "ANSWER" field in the test set.

This publication refers to the dataset used in the competition.

This is a dataset from the FinCausal 2025 competition. It is designed for participants to use it to fine-tune their models and complete the task with the highest possible similarity to the gold standard, according to the established metrics.

It consists of texts annotated by linguists, where a context, an abstractive question, and its corresponding extractive answer—which addresses the causal nature of the question—are provided.

There are two versions available: one in English and one in Spanish.

The project’s aims are to: (1) analyse the current level of usage and acceptance of non-sexist language among the group of pre-service teacher selected in the study; and (2) investigate the correlation between the language of instruction (Spanish vs. English) and the participants’ stance on this issue.

The corpus selected for the analysis is derived from a questionnaire in Spanish, completed by 348 trainee teachers enrolled in pre-primary and primary education programmes in Spain during the 2021–2022 academic year. The first part focused on collecting attributive information and defining the characteristics of the sample. It also included a mandatory written informed consent form. The remainder of the questionnaire was divided into three main sections, comprising 12 closed-ended items. These items explored: participants’ use and perception of inclusive language (IL) in an academic context (Section 1); their perception of professors’ use of IL (Section 2); and their intention to use IL with their future students (Section 3).