Related papers: Low Resource Multi-Task Sequence Tagging -- Revisi…

In model serving, having one fixed model during the entire often life-long inference process is usually detrimental to model performance, as data distribution evolves over time, resulting in lack of reliability of the model trained on…

Few-shot learning aims to handle previously unseen tasks using only a small amount of new training data. In preparing (or meta-training) a few-shot learner, however, massive labeled data are necessary. In the real world, unfortunately,…

Large-scale Multi-label Text Classification (LMTC) has a wide range of Natural Language Processing (NLP) applications and presents interesting challenges. First, not all labels are well represented in the training set, due to the very large…

Federated learning is a promising paradigm that utilizes distributed client resources while preserving data privacy. Most existing FL approaches assume clients possess labeled data, however, in real-world scenarios, client-side labels are…

Multi-label classification is a widely encountered problem in daily life, where an instance can be associated with multiple classes. In theory, this is a supervised learning method that requires a large amount of labeling. However,…

Current language models require a lot of training data to obtain high performance. For Relation Classification (RC), many datasets are domain-specific, so combining datasets to obtain better performance is non-trivial. We explore a…

Visual knowledge bases such as Visual Genome power numerous applications in computer vision, including visual question answering and captioning, but suffer from sparse, incomplete relationships. All scene graph models to date are limited to…

Most information in our world is organized hierarchically; however, many Deep Learning approaches do not leverage this semantically rich structure. Research suggests that human learning benefits from exploiting the hierarchical structure of…

Improving performance in multiple domains is a challenging task, and often requires significant amounts of data to train and test models. Active learning techniques provide a promising solution by enabling models to select the most…

Most Semantic Role Labeling (SRL) approaches are supervised methods which require a significant amount of annotated corpus, and the annotation requires linguistic expertise. In this paper, we propose a Multi-Task Active Learning framework…

Multi-source domain adaptation aims at leveraging the knowledge from multiple tasks for predicting a related target domain. Hence, a crucial aspect is to properly combine different sources based on their relations. In this paper, we…

This paper is concerned with structured machine learning, in a supervised machine learning context. It discusses how to make joint structured learning on interdependent objects of different nature, as well as how to enforce logical…

To improve deep-learning performance in low-resource settings, many researchers have redesigned model architectures or applied additional data (e.g., external resources, unlabeled samples). However, there have been relatively few…

Meta learning has been widely used to exploit rich-resource source tasks to improve the performance of low-resource target tasks. Unfortunately, most existing meta learning approaches treat different source tasks equally, ignoring the…

Semantic role labeling (SRL) has multiple disjoint label sets, e.g., VerbNet and PropBank. Creating these datasets is challenging, therefore a natural question is how to use each one to help the other. Prior work has shown that cross-task…

The data made available for analysis are becoming more and more complex along several directions: high dimensionality, number of examples and the amount of labels per example. This poses a variety of challenges for the existing machine…

Sentiment classification involves quantifying the affective reaction of a human to a document, media item or an event. Although researchers have investigated several methods to reliably infer sentiment from lexical, speech and body language…

Handwritten Text Recognition (HTR) for Arabic-script languages benefits from cross-language joint training under low-resource conditions, particularly when using CRNN-based models that combine convolutional encoders with sequence modeling.…

In this paper, we propose a novel approach for learning multi-label classifiers with the help of privileged information. Specifically, we use similarity constraints to capture the relationship between available information and privileged…

Multitask learning is widely used in practice to train a low-resource target task by augmenting it with multiple related source tasks. Yet, naively combining all the source tasks with a target task does not always improve the prediction…