Related papers: Modeling Label Correlations for Second-Order Seman…

Word embeddings are effective intermediate representations for capturing semantic regularities between words, when learning the representations of text sequences. We propose to view text classification as a label-word joint embedding…

Sentence semantic matching is one of the fundamental tasks in natural language processing, which requires an agent to determine the semantic relation among input sentences. Recently, deep neural networks have achieved impressive performance…

Deep regression networks are widely used to tackle the problem of predicting a continuous value for a given input. Task-specialized approaches for training regression networks have shown significant improvement over generic approaches, such…

Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural…

Vector space methods that measure semantic similarity and relatedness often rely on distributional information such as co--occurrence frequencies or statistical measures of association to weight the importance of particular co--occurrences.…

Learning to construct text representations in end-to-end systems can be difficult, as natural languages are highly compositional and task-specific annotated datasets are often limited in size. Methods for directly supervising language…

This paper extends the class of ordinal regression models with a structured interpretation of the problem by applying a novel treatment of encoded labels. The net effect of this is to transform the underlying problem from an ordinal…

Many modern multiclass and multilabel problems are characterized by increasingly large output spaces. For these problems, label embeddings have been shown to be a useful primitive that can improve computational and statistical efficiency.…

In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a…

Most image-text retrieval work adopts binary labels indicating whether a pair of image and text matches or not. Such a binary indicator covers only a limited subset of image-text semantic relations, which is insufficient to represent…

Image similarity has been extensively studied in computer vision. In recent years, machine-learned models have shown their ability to encode more semantics than traditional multivariate metrics. However, in labelling semantic similarity,…

We introduce second-order vector representations of words, induced from nearest neighborhood topological features in pre-trained contextual word embeddings. We then analyze the effects of using second-order embeddings as input features in…

Labeled sequence transduction is a task of transforming one sequence into another sequence that satisfies desiderata specified by a set of labels. In this paper we propose multi-space variational encoder-decoders, a new model for labeled…

The extreme multi-label classification~(XMC) task involves learning a classifier that can predict from a large label set the most relevant subset of labels for a data instance. While deep neural networks~(DNNs) have demonstrated remarkable…

Detecting emotions expressed in text has become critical to a range of fields. In this work, we investigate ways to exploit label correlations in multi-label emotion recognition models to improve emotion detection. First, we develop two…

Most of the unsupervised dependency parsers are based on first-order probabilistic generative models that only consider local parent-child information. Inspired by second-order supervised dependency parsing, we proposed a second-order…

Contrastive learning methods enforce label distance relationships in feature space to improve representation capability for regression models. However, these methods highly depend on label information to correctly recover ordinal…

We propose a novel model for multi-label text classification, which is based on sequence-to-sequence learning. The model generates higher-level semantic unit representations with multi-level dilated convolution as well as a corresponding…

Extreme classification tasks are multi-label tasks with an extremely large number of labels (tags). These tasks are hard because the label space is usually (i) very large, e.g. thousands or millions of labels, (ii) very sparse, i.e. very…

Objects are usually associated with multiple attributes, and these attributes often exhibit high correlations. Modeling complex relationships between attributes poses a great challenge for multi-attribute learning. This paper proposes a…