Models for conversational question answering (ConvQA) over knowledge graphs (KGs) are usually trained and tested on benchmarks of gold QA pairs. This implies that training is …
P Jain, M Lapata - arXiv preprint arXiv:2407.09506, 2024 - arxiv.org
We focus on a conversational question answering task which combines the challenges of understanding questions in context and reasoning over evidence gathered from …