KGQA - Knowledge Graph Question Answering

NFDI4DS partners organize SharedTasks at TextGraphs-17 (Graph-based Methods for Natural Language Processing) co-located with ACL2024 in Bangkok, Thailand, 11-16 August, 2024.

TextGraph fosters investigation of synergies between methods for text and graph processing. This edition focuses on the fusion of LLMs with KGs. In line with this goal we propose a shared task on Text-Graph Representations for Knowledge Graph Question Answering (KGQA).

The shared task is to select a Knowledge Graph (KG) entity (out of several candidates) which correspond to an answer given a textual question. The specificity of the task is, that for each question-answer (Q-A) pair not only a textual Q-A pair is given, but also a graph of shortest paths in the KG from entities in query to the LLM-generated candidate entity (including links of the intermediate nodes). This way, participants easily may experiment with various strategies of text-graph modality fusion for the given task in a controllable manner.

So the goal is to learn how LLMs output can be enhanced with KGs. We propose a convenient testbed for that by pre-extracting the graph as there are many ways how this extraction can be done fragmenting the text-graph modality data fusion experiments.

Find detailed information on the workshop page: https://sites.google.com/view/textgraphs2024/home/shared-task