| Resumen |
The JOKER Lab at the Conference and Labs of the Evaluation Forum (CLEF) aims to foster research on automated processing of verbal humour, including tasks such as retrieval, classification, interpretation, generation, and translation. Despite the heady success of large language models, humour and wordplay automatic processing are far from being a solved problem. JOKER brings together experts from the social and computational sciences and encourages them to collaborate on shared tasks with quality-controlled annotated datasets. In 2024, we will offer entirely new shared tasks on humour-aware information retrieval, as well as fine-grained sentiment analysis and classification of humour for conversational agents. As in the past JOKER Labs, we will also make our data available for an unshared task that solicits novel use cases. In this paper, we provide a brief retrospective on the JOKER Labs, with a focus on the results and lessons learnt from last year’s iteration, and we preview the tasks to be held at JOKER 2024. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024. |
