Introduction We present a methodology to automatically evaluate the performance of patients during picture description tasks. Methods Transcriptions and audio recordings of the Cookie Theft picture description task were used. With 25 healthy elderly control (HC) samples and an information coverage measure, we automatically generated a population-specific referent. We then assessed 517 transcriptions (257 Alzheimer's disease [AD], 217 HC, and 43 mild cognitively impaired samples) according to their informativeness and pertinence against this referent. We extracted linguistic and phonetic metrics which previous literature correlated to early-stage AD. We trained two learners to distinguish HCs from cognitively impaired individuals. Results Our measures significantly ( P < .001) correlated with the severity of the cognitive impairment and the Mini–Mental State Examination score. The classification sensitivity was 81% (area under the curve of receiver operating characteristics = 0.79) and 85% (area under the curve of receiver operating characteristics = 0.76) between HCs and AD and between HCs and AD and mild cognitively impaired, respectively. Discussion An automated assessment of a picture description task could assist clinicians in the detection of early signs of cognitive impairment and AD.

Sentence representation at the semantic level is a challenging task for Natural Language Processing and Artificial Intelligence. Despite the advances in word embeddings (i.e. word vector representations), capturing sentence meaning is an open question due to complexities of semantic interactions among words. In this paper, we present an embedding method, which is aimed at learning unsupervised sentence representations from unlabeled text. We propose an unsupervised method that models a sentence as a weighted series of word embeddings. The weights of the word embeddings are fitted by using Shannon's word entropies provided by the Term Frequency-Inverse Document Frequency (TF-IDF) transform. The hyperparameters of the model can be selected according to the properties of data (e.g. sentence length and textual gender). Hyperparameter selection involves word embedding methods and dimensionalities, as well as weighting schemata. Our method offers advantages over existing methods: identifiable modules, short-term training, online inference of (unseen) sentence representations, as well as independence from domain, external knowledge and language resources. Results showed that our model outperformed the state of the art in well-known Semantic Textual Similarity (STS) benchmarks. Moreover, our model reached state-of-the-art performance when compared to supervised and knowledge-based STS systems.

No abstract

No abstract

In this paper we present a description of the role of definitional verbal patterns for the extraction of semantic relations. Several studies show that semantic relations can be extracted from analytic definitions contained in machine-readable dictionaries (MRDs). In addition, definitions found in specialised texts are a good starting point to search for different types of definitions where other semantic relations occur. The extraction of definitional knowledge from specialised corpora represents another interesting approach for the extraction of semantic relations. Here, we present a descriptive analysis of definitional verbal patterns in Spanish and the first steps towards the development of a system for the automatic extraction of definitional knowledge.