This micro-project was jointly performed by ILSP/ATHENA Research Centre, German Research Centre for Artificial Intelligence (DFKI) and OpenAIRE. The project is part of the Humane-AI-Net network of excellent research centres in AI. It contributes to this network in the following respects:

• Phase I: Two collections with News and scientific publications will be compiled in the areas of Health and Climate. The News collection will be built based on an existing dataset with News stories and ARC automated classification system in the areas of interest. 
   
• Phase II: In phase II, we will be developing/advancing, finetuning and evaluating the two subsystems. Concretely, the “claim analysis” subsystem encompasses (i) ARC previous work on “claim identification”, (ii) a retrieval engine fetching relevant scientific publications (based on our previous miniProject), and (iii) an evidence-synthesis module indicating whether the publications fetched and the scientists’ claims therein, support or refute the News claim under examination. DFKI will be examining both lexical and syntax-based representations, exploring their contribution to text simplification and evaluating (neural) simplification models.

Mini project outcomes:

1. 1 Conference paper published in European ACL 2024 (EACL Malta). Paper: https://aclanthology.org/2024.eacl-long.156/
2. 1 dataset (namely HCN) of news articles in the domain of Health and Climate Change. The dataset contains news articles, annotated with the major claim, claimer(s) and claim object(s).
3. 1 website demonstrator. Website: http://scinobo.ilsp.gr:1997/services. The services for claim identification and the retrieval engine can be found here: http://scinobo.ilsp.gr:1997/live-demo?HFSpace=inobo-scinobo-claim-verification.hf.space. The service for the text simplification can be found here: http://scinobo.ilsp.gr:1997/text-simplification.