Research Summary
My main research interests concern Medical Information Extraction and Retrieval for Clinical Decision Support.
My main research aims to reduce the Semantic Gap between queries and documents to improve Clinical Decision Support. The Semantic Gap is a long-standing problem in Information Retrieval (IR) posing a critical challenge in medical settings due to the large presence - within the medical language - of synonymous and polyseomus words, along with context specific expressions. Two main lines of work have emerged in the past years to tackle this issue: (i) the use of external knowledge resources to enhance query and document bag-of-words representations; and (ii) the use of semantic models, based on the distributional hypothesis, which perform semantic matching on latent representations of documents and queries. We are designing, developing, and evaluating novel methods to leverage authoritative external knowledge resources in both lines, trying to tackle from different angles our core problem. The research lies at the intersection between Information Retrieval and Information Extraction, as it requires to combine retrieval models with entity linking and relation extraction techniques.
My research also concerns the extraction and usage of semantic relations from text to improve the retrieval of medical case reports through the use of document-level machine-readable Semantic Networks. These networks can then be leverged to semantically represent and compare documents. To make use of Semantic Networks, it is necessary to extract and link relations between them. Relations are typically in the form of triples (s,p,o), where s stands for subject, p for predicate and o for object. Therefore, Relation Extraction methods, along with Link Prediction techniques on multi-relational data, are relevant aspects of my research focus.
Since January 2019, my research work is partially supported by the EXAMODE H2020 EU project (more information below). Besides ExaMode, I am also working in the BRAINTEASER H2020 EU project (more information below).
Interests
- Information Retrieval
- Neural IR
- Semantic Matching
- Query Reformulation
- Information Extraction
- Entity Linking
- Relation Extraction
- Link Prediction
- Deep Learning
- Medical IR
- Medical IE
Data, Software, and Events
Data
The SPARQL endpoint to access the GEC KB is available here.
The Gene Expression-Cancer Knolwedge Base (GEC KB) generated by the CORE system can be found here.
The TBGA dataset for Gene-Disease Association Extraction (GDAE) can be found here.
The runs, pools, plots, and analyses to reproduce SAFIR results are available here.
The runs used to perform experiments on Precision Medicine Query REFormulations (PM QREF) can be found here.
Software
The CoreKB platform for searching reliable facts over gene expression-cancer associations is available here.
The source code and info about the Collaborative Oriented Relation Extraction (CORE) system are available here.
The source code and info about the Semantic Knowledge Extractor Tool (SKET) are available here.
The source code and info about Biomedical Relation Extraction (BioRE) methods are available here.
The source code and info about the Semantic-Aware neural Framework for IR (SAFIR) can be found here.
Events
I am the Proceedings Chair of the 27th International Conference on Theory and Practice of Digital Libraries (TPDL 2023) to be held in Zadar from 26 to 29 September 2023: TPDL 2023
I was the Doctoral Consortium Chair of the 31st Symposium on Advanced Database System (SEBD 2023) to be held in Galzignano Terme (Padua) from 2 to 5 July 2023: SEBD 2023
I was the Program Chair of the 19th Conference on Information and Research science Connecting to Digital and Library science (IRCDL 2023) held in Bari from 23 to 24 February 2023: IRCDL 2023
I was the Proceedings Chair of the 2nd Design of Experimental Search & Information REtrieval Systems Conference (DESIRES 2021) held in Padua from 15 to 18 September 2021: DESIRES 2021
I was the Publicity Chair of the 11th Italian Information Retrieval Workshop (IIR 2021) held in Bari from 13 to 15 September 2021: IIR 2021
I was the Organization Chair of the 17th Italian Research Conference on Digital Libraries (IRCDL 2021) held virtually in Padua from 18 to 19 February 2021: IRCDL 2021
I have contributed to the organization of the 42nd Interational ACM SIGIR Conference on Research and Development in Information Retrieval held in Paris from 21 to 25 July 2019: SIGIR 2019
I have contributed to the organization of the 38th European Conference on Information Retrieval held in Padua from 20 to 23 March 2016: ECIR 2016
Research Projects
-
Exascale volumes of diverse data from distributed sources are continuously produced. Healthcare data stand out in the size produced (production is expected to be over 2000 exabytes in 2020), heterogeneity (many media, acquisition methods), included knowledge (e.g. diagnosis) and commercial value. The supervised nature of deep learning models requires large labeled, annotated data, which precludes models to extract knowledge and value. Examode solves this by allowing easy & fast, weakly supervised knowledge discovery of exascale heterogeneous data, limiting human interaction.
We are leader of the "Semantic knowledge discovery and visualisation" WP. The main goals of the WP are:- Develop relation extraction methods to automatically extract semantic relationships between authoritative concepts within un/semi-structured text.
- Leverage entity linking methods in conjunction with developed relation extraction techniques to create report-level semantic networks out of extracted concepts and relationships.
- Model report-level semantic networks through conceptual descriptive frameworks to empower data management and exploitation.
- Develop information retrieval methods to semantically connect and discover semantic networks associated with relevant medical reports.
- Develop information visualization and visual analytics methods for interacting with deep learning algorithm and improve their understandability.
Project No: 825292
Call: H2020-ICT-2018-2
Topic: Big Data technologies and extreme-scale analytics
Funding (UNIPD): 516.000€ -
Amyotrophic Lateral Sclerosis (ALS) and Multiple Sclerosis (MS) are chronic diseases characterized by progressive or alternate impairment of neurological functions (motor, sensory, visual, cognitive). Artificial Intelligence is the key to successfully satisfy these needs to: i) better describe disease mechanisms; ii) stratify patients according to their phenotype assessed all over the disease evolution; iii) predict disease progression in a probabilistic, time dependent fashion; iv) investigate the role of the environment; v) suggest interventions that can delay the progression of the disease. BRAINTEASER will integrate large clinical datasets with novel personal and environmental data collected using low-cost sensors and apps.
We are leader of the "Open Science and FAIR Data" WP. The main goals of the WP are:- Design of open ontologies to represent the data of the project and create knowledge bases to enrich and augment the value of the data.
- Design and implement methods for the evaluation of the FAIRification of the data and metadata produced by applying and reviewing the FAIR principles of the European Open Science Cloud (EOSC). Integration and sharing of research data with EOSC services.
- Design and implementation of the methods to expose the data as Linked Open Data and the services to favour their exploration and re-use.
- Organisation of three annual open evaluation challenges and sharing of the produced experimental data as open data Evaluation.
Project No: 101017598
Call: H2020-SC1-DTH-2020-1
Topic: Personalised early risk prediction, prevention and intervention based on Artificial Intelligence and Big Data technologies
Funding (UNIPD): 732.250€