Andrei Catalin Coman — accepted AI-conference papers

2025

Fast-and-Frugal Text-Graph Transformers are Effective Link Predictors

Andrei Catalin Coman, Christos Theodoropoulos, Marie-Francine Moens, James Henderson

ACL 2025finding

We propose Fast-and-Frugal Text-Graph (FnF-TG) Transformers, a Transformer-based framework that unifies textual and structural information for inductive link prediction in text-attributed knowledge graphs. We demonstrate that, by effectively encoding ego-graphs (1-hop neighbourhoods), we can reduce…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Strong and Efficient Baselines for Open Domain Conversational Question Answering

Andrei Catalin Coman, Gianni Barlacchi, Adrià de Gispert

EMNLP 2023short findings

Unlike the Open Domain Question Answering (ODQA) setting, the conversational (ODConvQA) domain has received limited attention when it comes to reevaluating baselines for both efficiency and effectiveness. In this paper, we study the State-of-the-Art (SotA) Dense Passage Retrieval (DPR) retriever and…

Cited by 0 Source ↗Scholar ↗