According to Wikipedia "In machine learning, multi-label classification and the strongly related problem of multi-output classification are variants of the classification problem where multiple labels may be assigned to each instance. Multi-label classification is a generalization of multiclass classification, which is the single-label problem of categorizing instances into precisely one of more than two classes; in the multi-label problem there is no constraint on how many of the classes the instance can be assigned to."
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
This paper introduces Random Multimodel Deep Learning (RMDL): a new ensemble, deep learning approach for classification.
Obstacles hindering the development of capsule networks for challenging NLP applications include poor scalability to large output spaces and less reliable routing processes.
Ranked #1 on Text Classification on RCV1 (P@1 metric)
In this study, we explore capsule networks with dynamic routing for text classification.
Ranked #5 on Sentiment Analysis on MR
A recently introduced text classifier, called SS3, has obtained state-of-the-art performance on the CLEF's eRisk tasks.
SS3 was created to deal with ERD problems naturally since: it supports incremental training and classification over text streams, and it can visually explain its rationale.
Ranked #1 on Depression Detection on eRisk 2017
Multi-label text classifiers need to be carefully regularized to prevent the severe over-fitting in the high dimensional space, and also need to take into account label dependencies in order to make accurate predictions under uncertainty.
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 propose a novel model for multi-label text classification, which is based on sequence-to-sequence learning.
We propose a new label tree-based deep learning model for XMTC, called AttentionXML, with two unique features: 1) a multi-label attention mechanism with raw text as input, which allows to capture the most relevant part of text to each label; and 2) a shallow and wide probabilistic label tree (PLT), which allows to handle millions of labels, especially for "tail labels".
However, naively applying deep transformer models to the XMC problem leads to sub-optimal performance due to the large output space and the label sparsity issue.