An arduous biomedical task involves condensing evidence derived from multiple interrelated studies, given a context as input, to generate reviews or provide answers autonomously. We named this task context-aware multi-document summarization (CA-MDS). Existing state-of-the-art (SOTA) solutions require truncation of the input due to the high memory demands, resulting in the loss of meaningful content. To address this issue effectively, we propose a novel approach called RAMSES, which employs a retrieve-and-rank technique for end-to-end summarization. The model acquires the ability to (i) index each document by modeling its semantic features, (ii) retrieve the most relevant ones, and (iii) generate a summary via token probability marginalization. To facilitate the evaluation, we introduce a new dataset, FAQSUMC19, which includes the synthesizing of multiple supporting papers to answer questions related to Covid-19. Our experimental findings demonstrate that RAMSES achieves notably superior ROUGE scores compared to state-of-the-art methodologies, including the establishment of a new SOTA for the generation of systematic literature reviews using MS2. Quality observation through human evaluation indicates that our model produces more informative responses than previous leading approaches.

Retrieve-and-Rank End-to-End Summarization of Biomedical Studies / Gianluca Moro, Luca Ragazzi, Lorenzo Valgimigli, Lorenzo Molfetta. - ELETTRONICO. - 14289:(2023), pp. 64-78. (Intervento presentato al convegno International Conference on Similarity Search and Applications tenutosi a Coruña, Spain nel 09/11/2023 - 11/11/2023) [10.1007/978-3-031-46994-7_6].

Retrieve-and-Rank End-to-End Summarization of Biomedical Studies

Gianluca Moro
;
Luca Ragazzi;Lorenzo Valgimigli;Lorenzo Molfetta
2023

Abstract

An arduous biomedical task involves condensing evidence derived from multiple interrelated studies, given a context as input, to generate reviews or provide answers autonomously. We named this task context-aware multi-document summarization (CA-MDS). Existing state-of-the-art (SOTA) solutions require truncation of the input due to the high memory demands, resulting in the loss of meaningful content. To address this issue effectively, we propose a novel approach called RAMSES, which employs a retrieve-and-rank technique for end-to-end summarization. The model acquires the ability to (i) index each document by modeling its semantic features, (ii) retrieve the most relevant ones, and (iii) generate a summary via token probability marginalization. To facilitate the evaluation, we introduce a new dataset, FAQSUMC19, which includes the synthesizing of multiple supporting papers to answer questions related to Covid-19. Our experimental findings demonstrate that RAMSES achieves notably superior ROUGE scores compared to state-of-the-art methodologies, including the establishment of a new SOTA for the generation of systematic literature reviews using MS2. Quality observation through human evaluation indicates that our model produces more informative responses than previous leading approaches.
2023
Similarity Search and Applications. SISAP 2023
64
78
Retrieve-and-Rank End-to-End Summarization of Biomedical Studies / Gianluca Moro, Luca Ragazzi, Lorenzo Valgimigli, Lorenzo Molfetta. - ELETTRONICO. - 14289:(2023), pp. 64-78. (Intervento presentato al convegno International Conference on Similarity Search and Applications tenutosi a Coruña, Spain nel 09/11/2023 - 11/11/2023) [10.1007/978-3-031-46994-7_6].
Gianluca Moro, Luca Ragazzi, Lorenzo Valgimigli, Lorenzo Molfetta
File in questo prodotto:
File Dimensione Formato  
moro_ragazzi_valgimigli_SISAP23-2.pdf

embargo fino al 26/10/2024

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 284 kB
Formato Adobe PDF
284 kB Adobe PDF   Visualizza/Apri   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/962117
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact