The semantic mismatch between query and document terms—i.e., the semantic gap—is a long-standing problem in Information Retrieval (IR). Two main linguistic features related to the semantic gap that can be exploited to improve retrieval are synonymy and polysemy. Recent works integrate knowledge from curated external resources into the learning process of neural language models to reduce the effect of the semantic gap. However, these knowledge-enhanced language models have been used in IR mostly for re-ranking and not directly for document retrieval. We propose the Semantic-Aware Neural Framework for IR (SAFIR), an unsupervised knowledge-enhanced neural framework explicitly tailored for IR. SAFIR jointly learns word, concept, and document representations from scratch. The learned representations encode both polysemy and synonymy to address the semantic gap. SAFIR can be employed in any domain where external knowledge resources are available. We investigate its application in the medical domain where the semantic gap is prominent and there are many specialized and manually curated knowledge resources. The evaluation on shared test collections for medical literature retrieval shows the effectiveness of SAFIR in terms of retrieving and ranking relevant documents most affected by the semantic gap.

Background: Databases are fundamental to advance biomedical science. However, most of them are populated and updated with a great deal of human effort. Biomedical Relation Extraction (BioRE) aims to shift this burden to machines. Among its different applications, the discovery of Gene-Disease Associations (GDAs) is one of BioRE most relevant tasks. Nevertheless, few resources have been developed to train models for GDA extraction. Besides, these resources are all limited in size—preventing models from scaling effectively to large amounts of data. Results: To overcome this limitation, we have exploited the DisGeNET database to build a large-scale, semi-automatically annotated dataset for GDA extraction. DisGeNET stores one of the largest available collections of genes and variants involved in human diseases. Relying on DisGeNET, we developed TBGA: a GDA extraction dataset generated from more than 700K publications that consists of over 200K instances and 100K gene-disease pairs. Each instance consists of the sentence from which the GDA was extracted, the corresponding GDA, and the information about the gene-disease pair. Conclusions: TBGA is amongst the largest datasets for GDA extraction. We have evaluated state-of-the-art models for GDA extraction on TBGA, showing that it is a challenging and well-suited dataset for the task. We made the dataset publicly available to foster the development of state-of-the-art BioRE models for GDA extraction.

In this work, we propose a novel framework to devise features that can be used by Query Performance Prediction (QPP) models for Neural Information Retrieval (NIR). Using the proposed framework as a periodic table of QPP components, practitioners can devise new predictors better suited for NIR. Through the framework, we detail what challenges and opportunities arise for QPPs at different stages of the NIR pipeline. We show the potential of the proposed framework by using it to devise two types of novel predictors. The first one, named MEMory-based QPP (MEM-QPP), exploits the similarity between test and train queries to measure how much a NIR system can memorize. The second adapts traditional QPPs into NIR-oriented ones by computing the query-corpus semantic similarity. By exploiting the inherent nature of NIR systems, the proposed predictors overcome, under various setups, the current State of the Art, highlighting -- at the same time -- the versatility of the framework in describing different types of QPPs.

The increasing availability of biomedical data creates valuable resources for developing new deep learning algorithms to support experts, especially in domains where collecting large volumes of annotated data is not trivial. Biomedical data include several modalities containing complementary information, such as medical images and reports: images are often large and encode low-level information, while reports include a summarized high-level description of the findings identified within data and often only concerning a small part of the image. However, only a few methods allow to effectively link the visual content of images with the textual content of reports, preventing medical specialists from properly benefitting from the recent opportunities offered by deep learning models. This paper introduces a multimodal architecture creating a robust biomedical data representation encoding fine-grained text representations within image embeddings. The architecture aims to tackle data scarcity (combining supervised and self-supervised learning) and to create multimodal biomedical ontologies. The architecture is trained on over 6,000 colon whole slide Images (WSI), paired with the corresponding report, collected from two digital pathology workflows. The evaluation of the multimodal architecture involves three tasks: WSI classification (on data from pathology workflow and from public repositories), multimodal data retrieval, and linking between textual and visual concepts. Noticeably, the latter two tasks are available by architectural design without further training, showing that the multimodal architecture that can be adopted as a backbone to solve peculiar tasks. The multimodal data representation outperforms the unimodal one on the classification of colon WSIs and allows to halve the data needed to reach accurate performance, reducing the computational power required and thus the carbon footprint. The combination of images and reports exploiting self-supervised algorithms allows to mine databases without needing new annotations provided by experts, extracting new information. In particular, the multimodal visual ontology, linking semantic concepts to images, may pave the way to advancements in medicine and biomedical analysis domains, not limited to histopathology.

Exa-scale volumes of medical data have been produced for decades. In most cases, the diagnosis is reported in free text, encoding medical knowledge that is still largely unexploited. In order to allow decoding medical knowledge included in reports, we propose an unsupervised knowledge extraction system combining a rule-based expert system with pre-trained Machine Learning (ML) models, namely the Semantic Knowledge Extractor Tool (SKET). Combining rule-based techniques and pre-trained ML models provides high accuracy results for knowledge extraction. This work demonstrates the viability of unsupervised Natural Language Processing (NLP) techniques to extract critical information from cancer reports, opening opportunities such as data mining for knowledge extraction purposes, precision medicine applications, structured report creation, and multimodal learning.