17 July 2019 in Proceedings of the AAAI Conference on Artificial Intelligence
Temporal word embeddings have been proposed to support the analysis of word meaning shifts during time and to study the evolution of languages. Different approaches have been proposed to generate vector representations of words that embed their meaning during a specific time interval. However, the training process used in these approaches is complex, may be inefficient or it may require large text corpora. As a consequence, these approaches may be difficult to apply in resource-scarce domains or by scientists with limited in-depth knowledge of embedding models. In this paper, we propose a new heuristic to train temporal word embeddings based on the Word2vec model. The heuristic consists in using atemporal vectors as a reference, i.e., as a compass, when training the representations specific to a given time interval. The use of the compass simplifies the training process and makes it more efficient. Experiments conducted using state-of-the-art datasets and methodologies suggest that our approach outperforms or equals comparable approaches while being more robust in terms of the required corpus size.
6 February 2021 in Applied Intelligence
10 November 2021 in Physical Review A
We address the use of neural networks (NNs) in classifying the environmental parameters of single-qubit dephasing channels. In particular, we investigate the performance of linear perceptrons and of two nonlinear NN architectures. At variance with time-series-based approaches, our goal is to learn a discretized probability distribution over the parameters using tomographic data at just two random instants of time. We consider dephasing channels originating either from classical noise or from the interaction with a bath of quantum oscillators. The parameters to be classified are the color of the classical noise or the Ohmicity parameter of the quantum environment. In both cases, we find that NNs are able to exactly classify parameters into 16 classes using noiseless data (a linear NN is enough for the color, whereas a single-layer NN is needed for the Ohmicity). In the presence of noisy data (e.g., coming from noisy tomographic measurements), the network is able to classify the color of the noise into 16 classes with about accuracy, whereas classification of Ohmicity turns out to be challenging. We also consider a more coarse-grained task and train the network to discriminate between two macroclasses corresponding to and , obtaining up to and accuracy using single-layer NNs.