A survey on event extraction for natural language understanding: Riding the biomedical literature wave

G Frisoni, G Moro, A Carbonaro - IEEE Access, 2021 - ieeexplore.ieee.org
Motivation: The scientific literature embeds an enormous amount of relational knowledge,
encompassing interactions between biomedical entities, like proteins, drugs, and symptoms …

Bioreader: a retrieval-enhanced text-to-text transformer for biomedical literature

G Frisoni, M Mizutani, G Moro… - Proceedings of the 2022 …, 2022 - aclanthology.org
The latest batch of research has equipped language models with the ability to attend over
relevant and factual information from non-parametric external sources, drawing a …

Efficient memory-enhanced transformer for long-document summarization in low-resource regimes

G Moro, L Ragazzi, L Valgimigli, G Frisoni, C Sartori… - Sensors, 2023 - mdpi.com
Long document summarization poses obstacles to current generative transformer-based
models because of the broad context to process and understand. Indeed, detecting long …

Carburacy: summarization models tuning and comparison in eco-sustainable regimes with a novel carbon-aware accuracy

G Moro, L Ragazzi, L Valgimigli - … of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Generative transformer-based models have reached cutting-edge performance in long
document summarization. Nevertheless, this task is witnessing a paradigm shift in …

Comprehensive analysis of knowledge graph embedding techniques benchmarked on link prediction

I Ferrari, G Frisoni, P Italiani, G Moro, C Sartori - Electronics, 2022 - mdpi.com
In knowledge graph representation learning, link prediction is among the most popular and
influential tasks. Its surge in popularity has resulted in a panoply of orthogonal embedding …

Efficient self-supervised metric information retrieval: a bibliography based method applied to COVID literature

G Moro, L Valgimigli - Sensors, 2021 - mdpi.com
The literature on coronaviruses counts more than 300,000 publications. Finding relevant
papers concerning arbitrary queries is essential to discovery helpful knowledge. Current …

Cogito ergo summ: abstractive summarization of biomedical papers via semantic parsing graphs and consistency rewards

G Frisoni, P Italiani, S Salvatori, G Moro - Proceedings of the AAAI …, 2023 - ojs.aaai.org
The automatic synthesis of biomedical publications catalyzes a profound research interest
elicited by literature congestion. Current sequence-to-sequence models mainly rely on the …

[HTML][HTML] Efficient text-image semantic search: A multi-modal vision-language approach for fashion retrieval

G Moro, S Salvatori, G Frisoni - Neurocomputing, 2023 - Elsevier
In this paper, we address the problem of multi-modal retrieval of fashion products. State-of-
the-art (SOTA) works proposed in literature use vision-and-language transformers to assign …

NLG-metricverse: An end-to-end library for evaluating natural language generation

G Frisoni, A Carbonaro, G Moro… - Proceedings of the …, 2022 - aclanthology.org
Driven by deep learning breakthroughs, natural language generation (NLG) models have
been at the center of steady progress in the last few years, with a ubiquitous task influence …

Text-to-text extraction and verbalization of biomedical event graphs

G Frisoni, G Moro, L Balzani - Proceedings of the 29th …, 2022 - aclanthology.org
Biomedical events represent complex, graphical, and semantically rich interactions
expressed in the scientific literature. Almost all contributions in the event realm orbit around …