Маленькие наборы данных
Related Papers
Robust Gram Embeddings
Word embedding models learn vectorial word representations that can be used in a variety of NLP applications. When training data is scarce, these models risk losing their gener- alization abilities …...
Neural language models as psycholinguistic subjects: Representations of syntactic state
AbstractWe investigate the extent to which the behavior of neural network language models reflects incremental representations of syntactic state. To do so, we employ experimental methodologies which were originally developed …...
Beyond Fine-tuning: Few-Sample Sentence Embedding Transfer
AbstractFine-tuning (FT) pre-trained sentence embedding models on small datasets has been shown to have limitations. In this paper we show that concatenating the embeddings from the pre-trained model with those …...
Challenging distributional models with a conceptual network of philosophical terms
AbstractComputational linguistic research on language change through distributional semantic (DS) models has inspired researchers from fields such as philosophy and literary studies, who use these methods for the exploration and …...
Curriculum Learning Effectively Improves Low Data VQA
AbstractVisual question answering (VQA) models, in particular modular ones, are commonly trained on large-scale datasets to achieve state-of-the-art performance. However, such datasets are sometimes not available. Further, it has been …...