Simple, Fast, Accurate Intent Classification and Slot

sentation label, while such ambiguity characteristic is ignored in the SLL and MLL methods Proceedings of the Twenty-Seventh International Joint Conference on Artiﬁcial Intelligence (IJCAI-18) 4595

Exploit Bounding Box Annotations for Multi-Label Object

sentation (feature view) for multi-label object recognition Another novelty of our work is the proposed LMNN CNN which effectively extracts local information from the strong labels 2 Related Works Our paper mainly relates to the topics of CNN based multi-label object recognition, multi-view and multi-instance learning and local and metric

MUSE: MUlti-atlas region Segmentation utilizing Ensembles of

sentation that was introduced in Balochand Davatzikos (2008),wede-ﬁne the anatomic equivalence class of S as a set of all possible ways of representing the morphology of that individual via a transformation of an atlas and a respective residual, obtained by varying transformation parameters, i e Q¼ Q h θ ðÞx: ThðÞ¼θðÞx SðÞx −R h θ

Hierarchy-Aware Global Model for Hierarchical Text Classification

extracts label-wise text features with hierarchy en-coders based on prior hierarchy information Moreover, the attention mechanism is introduced in MLC byMullenbach et al (2018) for ICD cod-ing Rios and Kavuluru(2018) trains label repre-sentation through basic GraphCNN and conducts mutli-label attention with residual shortcuts At-

Labeled LDA: A supervised topic model for credit attribution

label set Consequently, these models fall short as a solution to the credit attribution problem Be-cause labels have meaning to the people that as-signed them, a simple solution to the credit attri-bution problem is to assign a document’s words to its labels rather than to a latent and possibly less interpretable semantic space

Nonparametric Guidance of Autoencoder Representations using

the autoencoder training objective by adding label-speciﬁc output units in addition to the recon-struction This approach was also followed by Ranzato and Szummer (2008) for learning document representations The difﬁculty of this approach is that it complicates the task of learning the autoencoder repre-sentation

Orderless Recurrent Models for Multi-Label Classification

sentation to feed to the RNN: in [48], images and labels are projected to the same low-dimensional space to model the image-text relationship, while [32] uses the predicted class

Self-supervised Label Augmentation via Input Transformations

2009) (10 labels) with the self-supervision on rotation (4 labels), we learn the joint probability distribution on all possible combinations, i e , 40 labels This label augmentation method, which we refer to as self-supervised label augmentation (SLA), does not force any invariance to the transformations without assumption for the