Two papers accepted at ESWC 2024 Workshops

23 April 2024, by Cedric Möller

The Text2KG workshop at the 'ESWC-2024' accepted the following paper:

• "Incorporating Type Information Into Zero-Shot Relation Extraction" -  Cedric Möller and Ricardo Usbeck

Abstract: The task of zero-shot relation extraction focuses on the extraction of relations not seen during training time.
Commonly, additional information about the relation such as the relation name or a description of the relation is utilised.
In this work, we analyze whether a relation extractor can benefit from the inclusion of fine-grained type information about the involved entities.
This is based on the intuition that relation descriptions might contain ontological information on the domain and range of the entity types that are usually put into relation. For that, we follow a cross-encoding setup where we encode both, the entity information and relation information, as one sequence and learn to score the representation. We examine this method on several datasets and show that the inclusion of the fine-grained type information leads to an improvement in performance.

The NSLP workshop at the 'ESWC-2024' accepted the following paper:

• "Scholarly Question Answering using Large Language Models in the NFDI4DataScience Gateway" - Hamed Babaei Giglou, Tilahun Abedissa Taffa, Rana Abdullah, Aida Usmanova, Ricardo Usbeck, Jennifer D’Souza and Sören Auer

Abstract: This paper introduces a scholarly Question Answering (QA) system on top of the NFDI4DataScience Gateway, employing a Retrieval Augmented Generation-based (RAG) approach. The NFDI4DS Gateway, as a foundational framework, offers a unified and intuitive interface for querying various scientific databases using federated search. The RAG-based scholarly QA, powered by a Large Language Model (LLM), facilitates dynamic interaction with search results, enhancing filtering capabilities and fostering a conversational engagement with the Gateway search. The effectiveness of both the Gateway and the scholarly QA system is demonstrated through experimental analysis.

The papers will soon be available in our "Publications" section.