Әсер ету функциялары

AbstractModern deep learning models for NLP are notoriously opaque. This has motivated the development of methods for interpreting such models, e.g., via gradient-based saliency maps or the visualization of attention …...

AbstractIdentifying user geolocation in online social networks is an essential task in many location-based applications. Existing methods rely on the similarity of text and network structure, however, they suffer from …...

AbstractWidespread adoption of deep models has motivated a pressing need for approaches to interpret network outputs and to facilitate model debugging. Instance attribution methods constitute one means of accomplishing these …...

AbstractInfluence functions approximate the “influences” of training data-points for test predictions and have a wide variety of applications. Despite the popularity, their computational cost does not scale well with model …...

AbstractCustomer feedback can be an important signal for improving commercial machine translation systems. One solution for fixing specific translation errors is to remove the related erroneous training instances followed by …...