242 papers with code • 9 benchmarks • 24 datasets
Multi-Label Classification is the supervised learning problem where an instance may be associated with multiple labels. This is an extension of single-label classification (i.e., multi-class, or binary) where each instance is only associated with a single class label.
The field of medical diagnostics contains a wealth of challenges which closely resemble classical machine learning problems; practical constraints, however, complicate the translation of these endpoints naively into classical architectures.
We propose sparsemax, a new activation function similar to the traditional softmax, but able to output sparse probabilities.
These algorithms are not directly applicable to large-scale learning problems since they scale poorly with the dimensionality of the gradients and the number of tasks.
In particular, the prediction of aspect-sentiment pairs is converted into multi-label classification, aiming to capture the dependency between words in a pair.
We present a feature vector formation technique for documents - Sparse Composite Document Vector (SCDV) - which overcomes several shortcomings of the current distributional paragraph vector representations that are widely used for text representation.
Due to this nature, the multi-label text classification task is often considered to be more challenging compared to the binary or multi-class text classification problems.
We also provide a theoretical analysis that justifies the use of XMC over link prediction and motivates integrating XR-Transformers, a powerful method for solving XMC problems, into the GIANT framework.
The task of Fine-grained Entity Type Classification (FETC) consists of assigning types from a hierarchy to entity mentions in text.