Word meaning changes over time, depending on linguistic and extra-linguistic factors. Associating a word's correct meaning in its historical context is a central challenge in diachronic research, and is relevant to a range of NLP tasks, including information retrieval and semantic search in historical texts. Bayesian models for semantic change have emerged as a powerful tool to address this challenge, providing explicit and interpretable representations of semantic change phenomena. However, while corpora typically come with rich metadata, existing models are limited by their inability to exploit contextual information (such as text genre) beyond the document timestamp. This is particularly critical in the case of ancient languages, where lack of data and long diachronic span make it harder to draw a clear distinction between polysemy (the fact that a word has several senses) and semantic change (the process of acquiring, losing, or changing senses), and current systems perform poorly on these languages. We develop GASC, a dynamic semantic change model that leverages categorical metadata about the texts' genre to boost inference and uncover the evolution of meanings in Ancient Greek corpora. In a new evaluation framework, our model achieves improved predictive performance compared to the state of the art.

ObjectivesVariable prevalence and treatment of breakthrough pain (BTP) in different clinical contexts are partially due to the lack of reliable/validated diagnostic tools with prognostic capability. We report the statistical basis and performance analysis of a novel BTP scoring system based on the naïve Bayes classifier (NBC) approach and an 11-item IQ-BTP validated questionnaire. This system aims at classifying potential BTP presence in three likelihood classes: “High,” “Intermediate,” and “Low.”MethodsOut of a training set of n=120 mixed chronic pain patients, predictors associated with the BTP likelihood variables (Pearson’s χ2 and/or Fisher’s exact test) were employed for the NBC planning. Adjusting the binary classification to a three–likelihood classes case enabled the building of a scoring algorithm and to retrieve the score of each predictor’s answer options and the Patient’s Global Score (PGS). The latter medians were used to establish the NBC thresholds, needed to evaluate the scoring system performance (leave-one-out cross-validation).ResultsMedians of PGS in the “High,” “Intermediate,” and “Low” likelihood classes were 3.44, 1.53, and −2.84, respectively. Leading predictors for the model (based on score differences) were flair frequency (ΔS=1.31), duration (ΔS=5.25), and predictability (ΔS=1.17). Percentages of correct classification were 63.6% for the “High” and of 100.0% for either the “Intermediate” and “Low” likelihood classes; overall accuracy of the scoring system was 90.9%.ConclusionThe NBC-based BTP scoring system showed satisfactory performance in classifying potential BTP in three likelihood classes. The reliability, flexibility, and simplicity of this statistical approach may have significant relevance for BTP epidemiology and management. These results need further impact studies to generalize our findings.

Prediction of subject age from brain anatomical MRI has the potential to provide a sensitive summary of brain changes, indicative of different neurodegenerative diseases. However, existing studies typically neglect the uncertainty of these predictions. In this work we take into account this uncertainty by applying methods of functional data analysis. We propose a penalised functional quantile regression model of age on brain structure with cognitively normal (CN) subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI), and use it to predict brain age in Mild Cognitive Impairment (MCI) and Alzheimer’s Disease (AD) subjects. Unlike the machine learning approaches available in the literature of brain age prediction, which provide only point predictions, the outcome of our model is a prediction interval for each subject.

Language is a complex and dynamic system. If we consider word meaning, which is the scope of lexical semantics, we observe that some words have several meanings, thus displaying lexical polysemy. In this article, we present the first phase of a project that aims at computationally modelling Ancient Greek semantics over time. Our system is based on Bayesian learning and on the Diorisis Ancient Greek corpus, which we have built for this purpose. We illustrate preliminary results in light of expert annotation, and take this opportunity to discuss the role of computational systems and human analysis in a complex research area like historical semantics. On the one hand, computational approaches allow us to model large corpora of texts. On the other hand, a long and rich scholarly tradition in Ancient Greek has provided us with valuable insights into the mechanisms of semantic change (cf. e.g. Leiwo, M. (2012). Introduction: variation with multiple faces. In Leiwo, M., Halla-aho, H., and Vierros, M. (eds), Variation and Change in Greek and Latin, Helsinki: Suomen Ateenan-instituutin säätiö, pp. 1–11.). In this article, we show that these qualitative analyses can be leveraged to support and complement the computational modelling.

Prediction of subject age from brain anatomical MRI has the potential to provide a sensitive summary of brain changes, indicative of different neurodegenerative diseases. However, existing studies typically neglect the uncertainty of these predictions. In this work we take into account this uncertainty by applying methods of functional data analysis. We propose a penalised functional quantile regression model of age on brain structure with cognitively normal (CN) subjects in the Alzheimer’s Disease Neuroimaging Initiative (ADNI), and use it to predict brain age in Mild Cognitive Impairment (MCI) and Alzheimer’s Disease (AD) subjects. Unlike the machine learning approaches available in the literature of brain age prediction, which provide only point predictions, the outcome of our model is a prediction interval for each subject.