1,720,983 research outputs found
18th Italian Research Conference on Digital Libraries: Information and Research Science connecting to Digital and Library Science
Full text linkDetection of Adverse Drug Events from Social Media Texts – Research Project Overview
No full textThis paper presents an overview of the current research project on the detection of Adverse Drug Events from social media texts led by the Artificial Intelligence Laboratory of Udine (AILAB Udine). In the latest years, patients started reporting Adverse Drug Events (ADEs) on social media and similar online outlets, making it necessary to monitor them for pharmacovigilance purposes. For this reason, systems for the automatic extraction of ADEs are becoming an important research topic in the Natural Language Processing community. In this paper we present our research project, focused on the Detection, Extraction and Normalization of ADEs, detailing its objectives, achievements and future directions
Increasing adverse drug events extraction robustness on social media: Case study on negation and speculation
No full textIn the last decade, an increasing number of users have started reporting adverse drug events (ADEs) on social media platforms, blogs, and health forums. Given the large volume of reports, pharmacovigilance has focused on ways to use natural language processing (NLP) techniques to rapidly examine these large collections of text, detecting mentions of drug-related adverse reactions to trigger medical investigations. However, despite the growing interest in the task and the advances in NLP, the robustness of these models in face of linguistic phenomena such as negations and speculations is an open research question. Negations and speculations are pervasive phenomena in natural language and can severely hamper the ability of an automated system to discriminate between factual and non-factual statements in text. In this article, we take into consideration four state-of-the-art systems for ADE detection on social media texts. We introduce SNAX, a benchmark to test their performance against samples containing negated and speculated ADEs, showing their fragility against these phenomena. We then introduce two possible strategies to increase the robustness of these models, showing that both of them bring significant increases in performance, lowering the number of spurious entities predicted by the models by 60% for negation and 80% for speculations
Negation Detection for Robust Adverse Drug Event Extraction From Social Media Texts
Full text linkAdverse Drug Event (ADE) extraction from user-generated content has gained popularity as a tool to aid researchers and pharmaceutical companies to monitor side effect of drugs in the wild. Automatic models can rapidly examine large collections of social media texts. However it is currently unknown if such models are robust in face of linguistic phenomena such as negation and speculation, which are pervasive across language varieties. We evaluate three state-of-the-art systems, showing their fragility against negation, and then we introduce two possible strategies to increase the robustness of these models: (i) a pipeline approach, using a specific component for negation detection; (ii) an augmentation of the dataset with artificially negated samples to further train the models. We show that both strategies bring significant increases in performance
Paving the Way for Personalized Museums Tours in the Metaverse
No full textMuseums play a central role in the preservation and communication of human history. With the advent of powerful and accessible Virtual Reality technologies, new Metaverse Museums started being developed, creating new possibilities for discovering and experiencing knowledge from all over the world. In anticipation of this technology becoming more widely adopted, we must prepare tools to aid future visitors in finding and navigating the museums and exhibitions which are more relevant to their current interests. In this light, Deep Learning methods could be of great use for modeling Metaverse museums, retrieving the most relevant ones, and creating personalized tours of the artifacts contained within them. In this paper, we present our research project, “Personalized Museum Tours in the Metaverse” led by the Artificial Intelligence Laboratory of Udine (AILAB Udine), detailing its objectives, proposed methodology, and future directions
A perspective on Artificial Intelligence for digital pharmacovigilance in pandemics
No full textDuring the COVID-19 pandemic, we witnessed the fastest massive vaccine rollout in human history. Like any other drug, vaccines have side effects, which might be harmful to the public trust when not properly communicated, hampering vaccination campaigns planned by governments. Therefore, it is of strategic importance to provide AI-empowered tools for monitoring their communication and feedback of social media users. At the same time, adverse drug event extraction from user-generated content has gained popularity as a tool to aid researchers and pharmaceutical companies in monitoring the side effects of drugs in a real-world setting. Using these innovative pharmacovigilance (PV) tools, it is possible to use natural language processing (NLP) techniques to monitor social media outlets and gain insights on how the population is reacting to information about the pandemic, vaccines, and measurement to contain infections, both from a psychological and physiological perspective. Data collected from social media allow us to draw comparisons between the different areas of the world, times, and living conditions, discovering meaningful patterns. Indeed, some of the socio-economic factors that characterize different geographical areas (e.g., general lifestyle, food choices, sports activities, ethnicity, economic status etc.) can have a tangible impact on the population's understanding and adherence to therapies, containing measures and more in general and diseases. In this article, we explore the possibilities of NLP for PV in the form of gathering and analyzing social media signals. We use as a case study the recent COVID-19 pandemic and show how the data collected on social media platforms such as Twitter since the start of the vaccination campaigns can provide useful insights and how this could help in future critical situations
Extensive evaluation of transformer-based architectures for adverse drug events extraction
No full textAdverse Drug Event (ADE) extraction is one of the core tasks in digital pharmacovigilance, especially when applied to informal texts. This task has been addressed by the Natural Language Processing community using large pre-trained language models, such as BERT. Despite the great number of Transformer-based architectures used in the literature, it is unclear which of them has better performances and why. Therefore, in this paper we perform an extensive evaluation and analysis of 19 Transformer-based models for ADE extraction on informal texts. We compare the performance of all the considered models on two datasets with increasing levels of informality (forums posts and tweets). We also combine the purely Transformer-based models with two commonly-used additional processing layers (CRF and LSTM), and analyze their effect on the models performance. Furthermore, we use a well-established feature importance technique (SHAP) to correlate the performance of the models with a set of features that describe them: model category (AutoEncoding, AutoRegressive, Text-to-Text), pre-training domain, training from scratch, and model size in number of parameters. At the end of our analyses, we identify a list of take-home messages that can be derived from the experimental data
Filling the Lacunae in ancient Latin inscriptions
No full textInscriptions are a testimony to the past but their poor condition, caused by the deterioration of the material on which they are engraved upon, often makes them partially or completely illegible. The process of restoring these inscriptions is time-consuming and requires the involvement of an expert epigraphist. It is possible to speed-up this process by adopting a semi-automatic assisting tool based on deep neural networks. This work describes a methodology, from the acquisition of the inscriptions to the description of four possible approaches, to predict the missing text in a Latin inscription, that our research team plans to implement in the near future as part of an interdisciplinary research project
BERT Prescriptions to avoid unwanted headaches: A comparison of transformer architectures for adverse drug event detection
Full text linkPretrained transformer-based models, such as BERT and its variants, have become a common choice to obtain state-of-the-art performances in NLP tasks. In the identification of Adverse Drug Events (ADE) from social media texts, for example, BERT architectures rank first in the leaderboard. However, a systematic comparison between these models has not yet been done. In this paper, we aim at shedding light on the differences between their performance analyzing the results of 12 models, tested on two standard benchmarks. SpanBERT and PubMedBERT emerged as the best models in our evaluation: this result clearly shows that span-based pretraining gives a decisive advantage in the precise recognition of ADEs, and that in-domain language pretraining is particularly useful when the transformer model is trained just on biomedical text from scratch
- …
