We invite the community to participate in the shared task we organize and consider working on data from our previous shared tasks in the scope of the CASE workshop @ EACL 2024 (https://emw.ku.edu.tr/case-2024/).
Recent & Active Shared task: *T1: Climate Activism Stance and Hate Event Detection*
Hate speech detection and stance detection are some of the most important aspects of event identification during climate change activism events. In the case of hate speech detection, the event is the occurrence of hate speech, the entity is the target of the hate speech, and the relationship is the connection between the two. The hate speech event has targets to which hate is directed. Identification of targets is an important task within hate speech event detection. Additionally, stance event detection is an important part of assessing the dynamics of protests and activisms for climate change. This helps to understand whether the activist movements and protests are being supported or opposed. This task will have three subtasks (i) Hate speech identification (ii) Targets of Hate Speech Identification (iii) Stance Detection.
*Codalab Link:* https://codalab.lisn.upsaclay.fr/competitions/16206 https://codalab.lisn.upsaclay.fr/competitions/16206
Registration: In order to register for the shared task, please send a request in Codalab. The organizers will approve requests on a daily basis.
*GitHub Page:* https://github.com/therealthapa/case2024-climate https://github.com/therealthapa/case2024-climate *Timeline*: Training & Evaluation data available: Nov 1, 2023 Test data available: Nov 30, 2023 Test start: Nov 30, 2023 Test end: Jan 5, 2024 System Description Paper submissions due: Jan 12, 2024 Notification to authors after review: Jan 26, 2024 Camera ready: Jan 30, 2024 CASE Workshop: 21-22 Mar, 2024 Previous shared tasks for working on regular papers (no official competition), please see the regular paper submission timeline: PT1: MULTILINGUAL PROTEST NEWS DETECTION
The performance of an automated system depends on the target event type as it may be broad or potentially the event trigger(s) can be ambiguous. The context of the trigger occurrence may need to be handled as well. For instance, the ‘protest’ event type may be synonymous with ‘demonstration’ or not in a specific context. Moreover, the hypothetical cases such as future protest plans may need to be excluded from the results. Finally, the relevance of a protest depends on the actors as in a contentious political event only citizen-led events are in the scope. This challenge becomes even harder in a cross-lingual and zero-shot setting in case training data are not available in new languages. We tackle the task in four steps and hope state-of-the-art approaches will yield optimal results.
Contact person: Ali Hürriyetoğlu (ali.hurriyetoglu@gmail.com)
Github: https://github.com/emerging-welfare/case-2022-multilingual-event
PT2: EVENT CAUSALITY IDENTIFICATION
Causality is a core cognitive concept and appears in many natural language processing (NLP) works that aim to tackle inference and understanding. We are interested in studying event causality in the news and, therefore, introduce the Causal News Corpus. The Causal News Corpus consists of 3,767 event sentences extracted from protest event news, that have been annotated with sequence labels on whether it contains causal relations or not. Subsequently, causal sentences are also annotated with Cause, Effect and Signal spans. Our subtasks work on the Causal News Corpus, and we hope that accurate, automated solutions may be proposed for the detection and extraction of causal events in news.
Contact person: Fiona Anting Tan (tan.f@u.nus.edu)
Github: https://github.com/tanfiona/CausalNewsCorpus
PT3: MULTIMODAL HATE SPEECH EVENT DETECTION
Hate speech detection is one of the most important aspects of event identification during political events like invasions. In the case of hate speech detection, the event is the occurrence of hate speech, the entity is the target of the hate speech, and the relationship is the connection between the two. Since multimodal content is widely prevalent across the internet, the detection of hate speech in text-embedded images is very important. Given a text-embedded image, this task aims to automatically identify the hate speech and its targets. This task will have two subtasks.
Contact person: Surendrabikram Thapa (surendrabikram@vt.edu)
Codalab page: https://codalab.lisn.upsaclay.fr/competitions/16203
Github: https://github.com/therealthapa/case2023_task4
Note: The organizers follows a specific timeline. Please see the Codalab page.