Уверенность в предсказании

Geolocation prediction is vital to geospatial applications like localised search and local event detection. Predominately, social media geolocation models are based on full text data, including common words with no …...

AbstractSupervised methods have achieved remarkable results in disfluency detection. However, in real-world scenarios, human-annotated data is difficult to obtain. Recent works try to handle disfluency detection with unsupervised self-training, which …...

AbstractGenre identification is a kind of non-topic text classification. The main difference between this task and topic classification is that genre, unlike topic, usually cannot be expressed just by some …...

AbstractDiscriminative pre-trained language models (PrLMs) can be generalized as denoising auto-encoders that work with two procedures, ennoising and denoising. First, an ennoising process corrupts texts with arbitrary noising functions to …...

AbstractSelf-training emerges as an important research line on domain adaptation. By taking the model’s prediction as the pseudo labels of the unlabeled data, self-training bootstraps the model with pseudo instances …...