Historical corpora are known to contain errors introduced by OCR (optical character recognition) methods used in the digitization process, often said to be degrading the performance of NLP systems. Correcting these errors manually is a time-consuming process and a great part of the automatic approaches have been relying on rules or supervised machine learning… We build on previous work on fully automatic unsupervised extraction of parallel data to train a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR […]

Voter models are well known in the interdisciplinary community, yet they haven’t been studied from the perspective of anomalous diffusion. In this paper we show that the original voter model exhibits ballistic regime… Non-linear transformations of the observation variable and time scale allows us to observe other regimes of anomalous diffusion as well as normal diffusion. We show that numerical simulation results coincide with derived analytical approximations describing the temporal evolution of the raw moments. (read more) PDF

Unsupervised anomalous sound detection is concerned with identifying sounds that deviate from what is defined as ‘normal’, without explicitly specifying the types of anomalies. A significant obstacle is the diversity and rareness of outliers, which typically prevent us from collecting a representative set of anomalous sounds… As a consequence, most anomaly detection methods use unsupervised rather than supervised machine learning methods. Nevertheless, we will show that anomalous sound detection can be effectively framed as a supervised classification problem if the […]

Image recognition with prototypes is considered an interpretable alternative for black box deep learning models. Classification depends on the extent to which a test image “looks like” a prototype… However, perceptual similarity for humans can be different from the similarity learnt by the model. A user is unaware of the underlying classification strategy and does not know which image characteristics (e.g., color or shape) is the dominant characteristic for the decision. We address this ambiguity and argue that prototypes should […]

Stereo depth estimation relies on optimal correspondence matching between pixels on epipolar lines in the left and right image to infer depth. Rather than matching individual pixels, in this work, we revisit the problem from a sequence-to-sequence correspondence perspective to replace cost volume construction with dense pixel matching using position information and attention… This approach, named STereo TRansformer (STTR), has several advantages: It 1) relaxes the limitation of a fixed disparity range, 2) identifies occluded regions and provides confidence of […]